From 906f2153182b6458ff3152193f22d3883fa8b5ea Mon Sep 17 00:00:00 2001
From: Hanzhang Ma <hanzhang@plunder.dbs.ifi.lmu.de>
Date: Sun, 12 May 2024 19:36:20 +0200
Subject: [PATCH] done

---
 main.ipynb | 10162 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 10050 insertions(+), 112 deletions(-)

diff --git a/main.ipynb b/main.ipynb
index d89f637..01ed6b1 100644
--- a/main.ipynb
+++ b/main.ipynb
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -25,7 +25,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -86,7 +86,7 @@
     "        half_dim = self.dim // 2\n",
     "        embeddings = math.log(10000) / (half_dim - 1)# 1/10000^(2i/d) = 1/10000^(i/(d/2)) = 10000^(-i/(d/2)\n",
     "        embeddings = torch.exp(torch.arange(half_dim, device=device) * -embeddings)\n",
-    "        embeddings = time[:, :, None] * embeddings[None, None, :]\n",
+    "        embeddings = time[:, None] * embeddings[None, :]\n",
     "        embeddings = torch.cat((embeddings.sin(), embeddings.cos()), dim=-1)\n",
     "        return embeddings\n",
     "        "
@@ -101,12 +101,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Block在init的时候创建了一个卷积层，一个归一化层，一个激活函数\n",
-    "# 前向的过程包括，首先卷积，再归一化，最后激活\n",
+    "# 前向的过程包括，首先卷typeignore积，再归一化，最后激活\n",
     "class Block(nn.Module):\n",
     "    def __init__(self, dim, dim_out, groups = 8):\n",
     "        super().__init__()\n",
@@ -124,30 +124,30 @@
     "\n",
     "        x = self.act(x)\n",
     "        return x\n",
-    "\n",
     "class ResnetBlock(nn.Module):\n",
-    "    def __init__(self, dim, dim_out, *, time_emb_dim = None, groups = 8):\n",
+    "    \"\"\"Deep Residual Learning for Image Recognition\"\"\"\n",
+    "    \n",
+    "    def __init__(self, dim, dim_out, *, time_emb_dim=None, groups=8):\n",
     "        super().__init__()\n",
     "        self.mlp = (\n",
-    "            nn.Sequential(\n",
-    "                nn.SiLU(), \n",
-    "                nn.Linear(time_emb_dim, dim_out)\n",
-    "            )\n",
-    "            if exists(time_emb_dim) else None\n",
+    "            nn.Sequential(nn.SiLU(), nn.Linear(time_emb_dim, dim_out))\n",
+    "            if exists(time_emb_dim)\n",
+    "            else None\n",
     "        )\n",
-    "        # 第一个块的作用是，将输入的特征图的维度从dim变成dim_out\n",
+    "\n",
     "        self.block1 = Block(dim, dim_out, groups=groups)\n",
-    "        self.block2 = Block(dim_out, dim_out=dim_out, groups=groups)\n",
+    "        self.block2 = Block(dim_out, dim_out, groups=groups)\n",
     "        self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()\n",
-    "    \n",
-    "    def forward(self, x, time_emb = None):\n",
+    "\n",
+    "    def forward(self, x, time_emb=None):\n",
+    "        print(x.shape)\n",
     "        h = self.block1(x)\n",
+    "        print(h.shape)\n",
+    "\n",
     "\n",
     "        if exists(self.mlp) and exists(time_emb):\n",
-    "            # 时间序列送到多层感知机里\n",
     "            time_emb = self.mlp(time_emb)\n",
-    "            # 为了让时间序列的维度和特征图的维度一致，所以需要增加一个维度\n",
-    "            h = rearrange(time_emb, 'b n -> b () n') + h\n",
+    "            h = rearrange(time_emb, \"b c -> b c 1 1\") + h\n",
     "\n",
     "        h = self.block2(h)\n",
     "        return h + self.res_conv(x)\n",
@@ -164,13 +164,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "class ConvNextBlock(nn.Module):\n",
     "    def __init__(self, dim, dim_out, *, time_emb_dim = None, mult = 2, norm = True):\n",
-    "        super().__init()\n",
+    "        super().__init__()\n",
     "        self.mlp = (\n",
     "            nn.Sequential(\n",
     "                nn.GELU(),\n",
@@ -191,11 +191,14 @@
     "        self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()\n",
     "\n",
     "    def forward(self, x, time_emb=None):\n",
+    "        # print(x.shape)\n",
     "        h = self.ds_conv(x)\n",
+    "        # print(h.shape)\n",
+    "\n",
     "\n",
     "        if exists(self.mlp) and exists(time_emb):\n",
     "            condition = self.mlp(time_emb)\n",
-    "            h = rearrange(time_emb, 'b c -> b c 1 1') + h\n",
+    "            h = h + rearrange(condition, 'b c -> b c 1 1')\n",
     "        h = self.net(h)\n",
     "        return h + self.res_conv(x)"
    ]
@@ -216,7 +219,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -225,7 +228,7 @@
     "        super().__init__()\n",
     "        self.scale = dim_head ** -0.5\n",
     "        self.heads = heads\n",
-    "        hidden_dim = dim_head * dim # 计算隐藏层的维度\n",
+    "        hidden_dim = dim_head * heads # 计算隐藏层的维度\n",
     "        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias=False) # 通过卷积层将输入的特征图的维度变成hidden_dim * 3\n",
     "        self.to_out = nn.Conv2d(hidden_dim, dim, 1)\n",
     "    \n",
@@ -249,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -291,7 +294,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -300,7 +303,7 @@
     "        super().__init__()\n",
     "        self.fn = fn\n",
     "        self.norm = nn.GroupNorm(1, dim)\n",
-    "    \n",
+    "\n",
     "    def forward(self, x):\n",
     "        x = self.norm(x)\n",
     "        return self.fn(x)"
@@ -326,11 +329,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
     "from functools import partial\n",
+    "\n",
     "class Unet(nn.Module):\n",
     "    def __init__(\n",
     "            self,\n",
@@ -348,6 +352,7 @@
     "        self.channels = channels\n",
     "\n",
     "        init_dim = default(init_dim, dim // 3 * 2) # 初始化维度 为 dim // 3 * 2 /dim // 3 * 2可能是经验得来的？\n",
+    "        print(f'init_dim:{init_dim}')\n",
     "        self.init_conv = nn.Conv2d(channels, init_dim, 7, padding=3) # 这里的kernel_size是7，padding是3，这样的设置是为了保持特征图的大小不变\n",
     "\n",
     "        dims = [init_dim, *map(lambda m: dim * m, dim_mults)] # dim * m是为了增加特征图的维度\n",
@@ -378,6 +383,7 @@
     "\n",
     "        for ind, (dim_in, dim_out) in enumerate(in_out):\n",
     "            is_last = ind >= (num_resolutions - 1)\n",
+    "            \n",
     "            self.downs.append(\n",
     "                nn.ModuleList(\n",
     "                    [\n",
@@ -391,8 +397,8 @@
     "        \n",
     "        # 因为中间的layer是单独的或者说不是对称的一部分，所以需要单独处理\n",
     "        mid_dim = dims[-1] # 下降到最后一层的维度 是dims的最后一个维度\n",
-    "        self.mid_blocks = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)\n",
-    "        self.mid_attn = Residual(PreNorm(mid_dim, LinearAttention))\n",
+    "        self.mid_block1 = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)\n",
+    "        self.mid_attn = Residual(PreNorm(mid_dim, Attention(mid_dim)))\n",
     "        self.mid_block2 = block_klass(mid_dim, mid_dim, time_emb_dim = time_dim)\n",
     "\n",
     "        # 上采样的layers\n",
@@ -416,6 +422,7 @@
     "        )\n",
     "\n",
     "    def forward(self, x, time):\n",
+    "        \n",
     "        x = self.init_conv(x)\n",
     "        t = self.time_mlp(time) if exists(self.time_mlp) else None\n",
     "        h = []\n",
@@ -429,7 +436,7 @@
     "            x = downsample(x)\n",
     "\n",
     "        # 中间的layer\n",
-    "        x = self.mid_blocks(x, t)\n",
+    "        x = self.mid_block1(x, t)\n",
     "        x = self.mid_attn(x)\n",
     "        x = self.mid_block2(x, t)\n",
     "\n",
@@ -455,7 +462,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -486,7 +493,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -522,7 +529,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -532,7 +539,7 @@
        "<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480>"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -556,7 +563,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -565,7 +572,7 @@
        "torch.Size([1, 3, 128, 128])"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -594,7 +601,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -612,7 +619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -622,7 +629,7 @@
        "<PIL.Image.Image image mode=RGB size=128x128>"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -633,7 +640,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -656,7 +663,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -693,7 +700,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -726,7 +733,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -761,66 +768,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "846cd4de5dc54577932d82e25d12a3eb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/30.9M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eafd5138ee6641609ef9ce06d2ef5054",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/5.18M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e1ea36ae914141a1828ae64507deb962",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating train split:   0%|          | 0/60000 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "06b2043f4d744a058618e5371b5ab960",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating test split:   0%|          | 0/10000 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from datasets import load_dataset\n",
     "\n",
@@ -832,7 +782,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -848,7 +798,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -894,11 +844,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
+    "from tqdm import tqdm\n",
     "@torch.no_grad()\n",
     "def p_sample(model, x, t, t_index):\n",
     "    betas_t = extract(betas, t, x.shape)\n",
@@ -906,7 +856,9 @@
     "        sqrt_one_minus_alphas_cumprod, t, x.shape\n",
     "    )\n",
     "    sqrt_recip_alphas_t = extract(sqrt_recip_alphas, t, x.shape)\n",
-    "\n",
+    "    \n",
+    "    # Equation 11 in the paper\n",
+    "    # Use our model (noise predictor) to predict the mean\n",
     "    model_mean = sqrt_recip_alphas_t * (\n",
     "        x - betas_t * model(x, t) / sqrt_one_minus_alphas_cumprod_t\n",
     "    )\n",
@@ -916,14 +868,10000 @@
     "    else:\n",
     "        posterior_variance_t = extract(posteriors_variance, t, x.shape)\n",
     "        noise = torch.randn_like(x)\n",
-    "        return model_mean + torch.sqrt(posterior_variance_t) * noise\n",
+    "        # Algorithm 2 line 4:\n",
+    "        return model_mean + torch.sqrt(posterior_variance_t) * noise \n",
     "\n",
+    "# Algorithm 2 (including returning all images)\n",
     "@torch.no_grad()\n",
-    "\n",
     "def p_sample_loop(model, shape):\n",
     "    device = next(model.parameters()).device\n",
     "\n",
-    "    b = shape[0]"
+    "    b = shape[0]\n",
+    "    # start from pure noise (for each example in the batch)\n",
+    "    img = torch.randn(shape, device=device)\n",
+    "    imgs = []\n",
+    "    print(imgs)\n",
+    "    for i in tqdm(reversed(range(0, timesteps)), desc='sampling loop time step', total=timesteps):\n",
+    "    # for i in range(0,timesteps):\n",
+    "        print(i)\n",
+    "        img = p_sample(model, img, torch.full((b,), i, device=device, dtype=torch.long), i)\n",
+    "        imgs.append(img.cpu().numpy())\n",
+    "    return imgs\n",
+    "\n",
+    "@torch.no_grad()\n",
+    "def sample(model, image_size, batch_size=16, channels=3):\n",
+    "    return p_sample_loop(model, shape=(batch_size, channels, image_size, image_size))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 模型训练"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "def num_to_groups(num, divisor):\n",
+    "    groups = num // divisor\n",
+    "    remainder = num % divisor\n",
+    "    arr = [divisor] * groups\n",
+    "    if remainder > 0:\n",
+    "        arr.append(remainder)\n",
+    "    return arr\n",
+    "\n",
+    "results_folder = Path(\"./results\")\n",
+    "results_folder.mkdir(exist_ok = True)\n",
+    "save_and_sample_every = 1000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "init_dim:18\n"
+     ]
+    }
+   ],
+   "source": [
+    "from torch.optim import Adam\n",
+    "\n",
+    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+    "\n",
+    "model = Unet(\n",
+    "    dim=image_size,\n",
+    "    channels=channels,\n",
+    "    dim_mults=(1, 2, 4,)\n",
+    ")\n",
+    "model.to(device)\n",
+    "\n",
+    "optimizer = Adam(model.parameters(), lr=1e-3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.5719783306121826\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.1572732925415039\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.08359217643737793\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.07419337332248688\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.0547160804271698\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.059942662715911865\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.06269419938325882\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.06426255404949188\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.05534350126981735\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.046698957681655884\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.051691167056560516\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.047971393913030624\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.04759804531931877\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.04247395694255829\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.057918716222047806\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.04689771309494972\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.05472369119524956\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.04564015567302704\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.04514097422361374\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.05501364916563034\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.039300259202718735\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.042815450578927994\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.040802985429763794\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.050201717764139175\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "Loss: 0.05320434644818306\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([128])\n",
+      "torch.Size([128, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n",
+      "torch.Size([96])\n",
+      "torch.Size([96, 1, 28, 28])\n"
+     ]
+    }
+   ],
+   "source": [
+    "from torchvision.utils import save_image\n",
+    "\n",
+    "epochs = 5\n",
+    "\n",
+    "for epoch in range(epochs):\n",
+    "    for step, batch in enumerate(dataloader):\n",
+    "      optimizer.zero_grad()\n",
+    "\n",
+    "      batch_size = batch[\"pixel_values\"].shape[0]\n",
+    "      batch = batch[\"pixel_values\"].to(device)\n",
+    "\n",
+    "      # Algorithm 1 line 3: sample t uniformally for every example in the batch\n",
+    "      t = torch.randint(0, timesteps, (batch_size,), device=device).long()\n",
+    "      loss = p_losses(model, batch, t, loss_type=\"huber\")\n",
+    "\n",
+    "      if step % 100 == 0:\n",
+    "        print(\"Loss:\", loss.item())\n",
+    "\n",
+    "      loss.backward()\n",
+    "      optimizer.step()\n",
+    "\n",
+    "      # save generated images\n",
+    "      if step != 0 and step % save_and_sample_every == 0:\n",
+    "        milestone = step // save_and_sample_every\n",
+    "        batches = num_to_groups(4, batch_size)\n",
+    "        all_images_list = list(map(lambda n: sample(model, batch_size=n, channels=channels), batches))\n",
+    "        all_images = torch.cat(all_images_list, dim=0)\n",
+    "        all_images = (all_images + 1) * 0.5\n",
+    "        save_image(all_images, str(results_folder / f'sample-{milestone}.png'), nrow = 6)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:   0%|          | 0/200 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "199\n",
+      "198\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:   1%|          | 2/200 [00:00<00:37,  5.30it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "197\n",
+      "196\n",
+      "195\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:   6%|▋         | 13/200 [00:00<00:07, 24.74it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "194\n",
+      "193\n",
+      "192\n",
+      "191\n",
+      "190\n",
+      "189\n",
+      "188\n",
+      "187\n",
+      "186\n",
+      "185\n",
+      "184\n",
+      "183\n",
+      "182\n",
+      "181\n",
+      "180\n",
+      "179\n",
+      "178\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  16%|█▌        | 31/200 [00:00<00:03, 50.58it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "177\n",
+      "176\n",
+      "175\n",
+      "174\n",
+      "173\n",
+      "172\n",
+      "171\n",
+      "170\n",
+      "169\n",
+      "168\n",
+      "167\n",
+      "166\n",
+      "165\n",
+      "164\n",
+      "163\n",
+      "162\n",
+      "161\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  24%|██▍       | 48/200 [00:01<00:02, 64.89it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "160\n",
+      "159\n",
+      "158\n",
+      "157\n",
+      "156\n",
+      "155\n",
+      "154\n",
+      "153\n",
+      "152\n",
+      "151\n",
+      "150\n",
+      "149\n",
+      "148\n",
+      "147\n",
+      "146\n",
+      "145\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  32%|███▎      | 65/200 [00:01<00:01, 72.07it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "144\n",
+      "143\n",
+      "142\n",
+      "141\n",
+      "140\n",
+      "139\n",
+      "138\n",
+      "137\n",
+      "136\n",
+      "135\n",
+      "134\n",
+      "133\n",
+      "132\n",
+      "131\n",
+      "130\n",
+      "129\n",
+      "128\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  42%|████▏     | 83/200 [00:01<00:01, 76.36it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "127\n",
+      "126\n",
+      "125\n",
+      "124\n",
+      "123\n",
+      "122\n",
+      "121\n",
+      "120\n",
+      "119\n",
+      "118\n",
+      "117\n",
+      "116\n",
+      "115\n",
+      "114\n",
+      "113\n",
+      "112\n",
+      "111\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  50%|████▉     | 99/200 [00:01<00:01, 78.04it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "110\n",
+      "109\n",
+      "108\n",
+      "107\n",
+      "106\n",
+      "105\n",
+      "104\n",
+      "103\n",
+      "102\n",
+      "101\n",
+      "100\n",
+      "99\n",
+      "98\n",
+      "97\n",
+      "96\n",
+      "95\n",
+      "94\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  58%|█████▊    | 116/200 [00:01<00:01, 78.94it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "93\n",
+      "92\n",
+      "91\n",
+      "90\n",
+      "89\n",
+      "88\n",
+      "87\n",
+      "86\n",
+      "85\n",
+      "84\n",
+      "83\n",
+      "82\n",
+      "81\n",
+      "80\n",
+      "79\n",
+      "78\n",
+      "77\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  67%|██████▋   | 134/200 [00:02<00:00, 79.49it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "76\n",
+      "75\n",
+      "74\n",
+      "73\n",
+      "72\n",
+      "71\n",
+      "70\n",
+      "69\n",
+      "68\n",
+      "67\n",
+      "66\n",
+      "65\n",
+      "64\n",
+      "63\n",
+      "62\n",
+      "61\n",
+      "60\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  76%|███████▌  | 151/200 [00:02<00:00, 79.35it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "59\n",
+      "58\n",
+      "57\n",
+      "56\n",
+      "55\n",
+      "54\n",
+      "53\n",
+      "52\n",
+      "51\n",
+      "50\n",
+      "49\n",
+      "48\n",
+      "47\n",
+      "46\n",
+      "45\n",
+      "44\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  84%|████████▍ | 169/200 [00:02<00:00, 79.85it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "43\n",
+      "42\n",
+      "41\n",
+      "40\n",
+      "39\n",
+      "38\n",
+      "37\n",
+      "36\n",
+      "35\n",
+      "34\n",
+      "33\n",
+      "32\n",
+      "31\n",
+      "30\n",
+      "29\n",
+      "28\n",
+      "27\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step:  93%|█████████▎| 186/200 [00:02<00:00, 79.88it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "26\n",
+      "25\n",
+      "24\n",
+      "23\n",
+      "22\n",
+      "21\n",
+      "20\n",
+      "19\n",
+      "18\n",
+      "17\n",
+      "16\n",
+      "15\n",
+      "14\n",
+      "13\n",
+      "12\n",
+      "11\n",
+      "10\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "sampling loop time step: 100%|██████████| 200/200 [00:03<00:00, 65.60it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "9\n",
+      "8\n",
+      "7\n",
+      "6\n",
+      "5\n",
+      "4\n",
+      "3\n",
+      "2\n",
+      "1\n",
+      "0\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7fa85d34dd90>"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# sample 64 images\n",
+    "def sample(model, image_size, batch_size=16, channels=3):\n",
+    "    return p_sample_loop(model, shape=(batch_size, channels, image_size, image_size))\n",
+    "\n",
+    "samples = sample(model, image_size=image_size, batch_size=64, channels=channels)\n",
+    "\n",
+    "# show a random one\n",
+    "random_index = 5\n",
+    "plt.imshow(samples[-1][random_index].reshape(image_size, image_size, channels), cmap=\"gray\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.animation as animation\n",
+    "\n",
+    "random_index = 53\n",
+    "\n",
+    "fig = plt.figure()\n",
+    "ims = []\n",
+    "for i in range(timesteps):\n",
+    "    im = plt.imshow(samples[i][random_index].reshape(image_size, image_size, channels), cmap=\"gray\", animated=True)\n",
+    "    ims.append([im])\n",
+    "\n",
+    "animate = animation.ArtistAnimation(fig, ims, interval=50, blit=True, repeat_delay=1000)\n",
+    "animate.save('diffusion.gif')\n",
+    "plt.show()"
    ]
   }
  ],