82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
#####################################################
|
|
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
|
|
#####################################################
|
|
import torch.nn as nn
|
|
from ..cell_operations import ResNetBasicblock
|
|
from .cells import InferCell
|
|
|
|
|
|
# The macro structure for architectures in NAS-Bench-201
|
|
class TinyNetwork(nn.Module):
|
|
|
|
def __init__(self, C, N, genotype, num_classes):
|
|
super(TinyNetwork, self).__init__()
|
|
self._C = C
|
|
self._layerN = N
|
|
|
|
self.stem = nn.Sequential(
|
|
nn.Conv2d(3, C, kernel_size=3, padding=1, bias=False),
|
|
nn.BatchNorm2d(C))
|
|
|
|
layer_channels = [C ] * N + [C*2 ] + [C*2 ] * N + [C*4 ] + [C*4 ] * N
|
|
layer_reductions = [False] * N + [True] + [False] * N + [True] + [False] * N
|
|
|
|
C_prev = C
|
|
self.cells = nn.ModuleList()
|
|
for index, (C_curr, reduction) in enumerate(zip(layer_channels, layer_reductions)):
|
|
if reduction:
|
|
cell = ResNetBasicblock(C_prev, C_curr, 2, True)
|
|
else:
|
|
cell = InferCell(genotype, C_prev, C_curr, 1)
|
|
self.cells.append( cell )
|
|
C_prev = cell.out_dim
|
|
self._Layer= len(self.cells)
|
|
|
|
self.lastact = nn.Sequential(nn.BatchNorm2d(C_prev), nn.ReLU(inplace=True))
|
|
self.global_pooling = nn.AdaptiveAvgPool2d(1)
|
|
self.classifier = nn.Linear(C_prev, num_classes)
|
|
|
|
self.requires_feature = True
|
|
|
|
def get_message(self):
|
|
string = self.extra_repr()
|
|
for i, cell in enumerate(self.cells):
|
|
string += '\n {:02d}/{:02d} :: {:}'.format(i, len(self.cells), cell.extra_repr())
|
|
return string
|
|
|
|
def extra_repr(self):
|
|
return ('{name}(C={_C}, N={_layerN}, L={_Layer})'.format(name=self.__class__.__name__, **self.__dict__))
|
|
|
|
def forward(self, inputs):
|
|
feature = self.stem(inputs)
|
|
for i, cell in enumerate(self.cells):
|
|
feature = cell(feature)
|
|
|
|
out = self.lastact(feature)
|
|
out = self.global_pooling( out )
|
|
out = out.view(out.size(0), -1)
|
|
logits = self.classifier(out)
|
|
|
|
if self.requires_feature:
|
|
return logits, out
|
|
else:
|
|
return logits
|
|
|
|
def _loss(self, input, target, return_logits=False):
|
|
logits, _ = self(input)
|
|
loss = self._criterion(logits, target)
|
|
|
|
return (loss, logits) if return_logits else loss
|
|
|
|
def step(self, input, target, args, shared=None, return_grad=False):
|
|
Lt, logit_t = self._loss(input, target, return_logits=True)
|
|
Lt.backward()
|
|
if args.grad_clip != 0:
|
|
nn.utils.clip_grad_norm_(self.get_weights(), args.grad_clip)
|
|
self.optimizer.step()
|
|
|
|
if return_grad:
|
|
grad = torch.nn.utils.parameters_to_vector([p.grad for p in self.get_weights()])
|
|
return logit_t, Lt, grad
|
|
else:
|
|
return logit_t, Lt |