Update visualization codes
This commit is contained in:
D-X-Y
172
exps-tf/GDAS.py
172
exps-tf/GDAS.py
@@ -1,172 +0,0 @@
|
||||
# [D-X-Y]
|
||||
# Run GDAS
|
||||
# CUDA_VISIBLE_DEVICES=0 python exps-tf/GDAS.py
|
||||
# Run DARTS
|
||||
# CUDA_VISIBLE_DEVICES=0 python exps-tf/GDAS.py --tau_max -1 --tau_min -1 --epochs 50
|
||||
#
|
||||
import os, sys, math, time, random, argparse
|
||||
import tensorflow as tf
|
||||
from pathlib import Path
|
||||
|
||||
lib_dir = (Path(__file__).parent / '..' / 'lib').resolve()
|
||||
if str(lib_dir) not in sys.path: sys.path.insert(0, str(lib_dir))
|
||||
|
||||
# self-lib
|
||||
from tf_models import get_cell_based_tiny_net
|
||||
from tf_optimizers import SGDW, AdamW
|
||||
from config_utils import dict2config
|
||||
from log_utils import time_string
|
||||
from models import CellStructure
|
||||
|
||||
|
||||
def pre_process(image_a, label_a, image_b, label_b):
|
||||
def standard_func(image):
|
||||
x = tf.pad(image, [[4, 4], [4, 4], [0, 0]])
|
||||
x = tf.image.random_crop(x, [32, 32, 3])
|
||||
x = tf.image.random_flip_left_right(x)
|
||||
return x
|
||||
return standard_func(image_a), label_a, standard_func(image_b), label_b
|
||||
|
||||
|
||||
class CosineAnnealingLR(object):
|
||||
def __init__(self, warmup_epochs, epochs, initial_lr, min_lr):
|
||||
self.warmup_epochs = warmup_epochs
|
||||
self.epochs = epochs
|
||||
self.initial_lr = initial_lr
|
||||
self.min_lr = min_lr
|
||||
|
||||
def get_lr(self, epoch):
|
||||
if epoch < self.warmup_epochs:
|
||||
lr = self.min_lr + (epoch/self.warmup_epochs) * (self.initial_lr-self.min_lr)
|
||||
elif epoch >= self.epochs:
|
||||
lr = self.min_lr
|
||||
else:
|
||||
lr = self.min_lr + (self.initial_lr-self.min_lr) * 0.5 * (1 + math.cos(math.pi * epoch / self.epochs))
|
||||
return lr
|
||||
|
||||
|
||||
|
||||
def main(xargs):
|
||||
cifar10 = tf.keras.datasets.cifar10
|
||||
|
||||
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
|
||||
x_train, x_test = x_train / 255.0, x_test / 255.0
|
||||
x_train, x_test = x_train.astype('float32'), x_test.astype('float32')
|
||||
|
||||
# Add a channels dimension
|
||||
all_indexes = list(range(x_train.shape[0]))
|
||||
random.shuffle(all_indexes)
|
||||
s_train_idxs, s_valid_idxs = all_indexes[::2], all_indexes[1::2]
|
||||
search_train_x, search_train_y = x_train[s_train_idxs], y_train[s_train_idxs]
|
||||
search_valid_x, search_valid_y = x_train[s_valid_idxs], y_train[s_valid_idxs]
|
||||
#x_train, x_test = x_train[..., tf.newaxis], x_test[..., tf.newaxis]
|
||||
|
||||
# Use tf.data
|
||||
#train_ds = tf.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(10000).batch(64)
|
||||
search_ds = tf.data.Dataset.from_tensor_slices((search_train_x, search_train_y, search_valid_x, search_valid_y))
|
||||
search_ds = search_ds.map(pre_process).shuffle(1000).batch(64)
|
||||
|
||||
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
|
||||
|
||||
# Create an instance of the model
|
||||
config = dict2config({'name': 'GDAS',
|
||||
'C' : xargs.channel, 'N': xargs.num_cells, 'max_nodes': xargs.max_nodes,
|
||||
'num_classes': 10, 'space': 'nas-bench-201', 'affine': True}, None)
|
||||
model = get_cell_based_tiny_net(config)
|
||||
num_iters_per_epoch = int(tf.data.experimental.cardinality(search_ds).numpy())
|
||||
#lr_schedular = tf.keras.experimental.CosineDecay(xargs.w_lr_max, num_iters_per_epoch*xargs.epochs, xargs.w_lr_min / xargs.w_lr_max)
|
||||
lr_schedular = CosineAnnealingLR(0, xargs.epochs, xargs.w_lr_max, xargs.w_lr_min)
|
||||
# Choose optimizer
|
||||
loss_object = tf.keras.losses.SparseCategoricalCrossentropy()
|
||||
w_optimizer = SGDW(learning_rate=xargs.w_lr_max, weight_decay=xargs.w_weight_decay, momentum=xargs.w_momentum, nesterov=True)
|
||||
a_optimizer = AdamW(learning_rate=xargs.arch_learning_rate, weight_decay=xargs.arch_weight_decay, beta_1=0.5, beta_2=0.999, epsilon=1e-07)
|
||||
#w_optimizer = tf.keras.optimizers.SGD(learning_rate=0.025, momentum=0.9, nesterov=True)
|
||||
#a_optimizer = tf.keras.optimizers.AdamW(learning_rate=xargs.arch_learning_rate, beta_1=0.5, beta_2=0.999, epsilon=1e-07)
|
||||
####
|
||||
# metrics
|
||||
train_loss = tf.keras.metrics.Mean(name='train_loss')
|
||||
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')
|
||||
valid_loss = tf.keras.metrics.Mean(name='valid_loss')
|
||||
valid_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='valid_accuracy')
|
||||
test_loss = tf.keras.metrics.Mean(name='test_loss')
|
||||
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')
|
||||
|
||||
@tf.function
|
||||
def search_step(train_images, train_labels, valid_images, valid_labels, tf_tau):
|
||||
# optimize weights
|
||||
with tf.GradientTape() as tape:
|
||||
predictions = model(train_images, tf_tau, True)
|
||||
w_loss = loss_object(train_labels, predictions)
|
||||
net_w_param = model.get_weights()
|
||||
gradients = tape.gradient(w_loss, net_w_param)
|
||||
w_optimizer.apply_gradients(zip(gradients, net_w_param))
|
||||
train_loss(w_loss)
|
||||
train_accuracy(train_labels, predictions)
|
||||
# optimize alphas
|
||||
with tf.GradientTape() as tape:
|
||||
predictions = model(valid_images, tf_tau, True)
|
||||
a_loss = loss_object(valid_labels, predictions)
|
||||
net_a_param = model.get_alphas()
|
||||
gradients = tape.gradient(a_loss, net_a_param)
|
||||
a_optimizer.apply_gradients(zip(gradients, net_a_param))
|
||||
valid_loss(a_loss)
|
||||
valid_accuracy(valid_labels, predictions)
|
||||
|
||||
# TEST
|
||||
@tf.function
|
||||
def test_step(images, labels):
|
||||
predictions = model(images)
|
||||
t_loss = loss_object(labels, predictions)
|
||||
|
||||
test_loss(t_loss)
|
||||
test_accuracy(labels, predictions)
|
||||
|
||||
print('{:} start searching with {:} epochs ({:} batches per epoch).'.format(time_string(), xargs.epochs, num_iters_per_epoch))
|
||||
|
||||
for epoch in range(xargs.epochs):
|
||||
# Reset the metrics at the start of the next epoch
|
||||
train_loss.reset_states() ; train_accuracy.reset_states()
|
||||
test_loss.reset_states() ; test_accuracy.reset_states()
|
||||
cur_tau = xargs.tau_max - (xargs.tau_max-xargs.tau_min) * epoch / (xargs.epochs-1)
|
||||
tf_tau = tf.cast(cur_tau, dtype=tf.float32, name='tau')
|
||||
cur_lr = lr_schedular.get_lr(epoch)
|
||||
tf.keras.backend.set_value(w_optimizer.lr, cur_lr)
|
||||
|
||||
for trn_imgs, trn_labels, val_imgs, val_labels in search_ds:
|
||||
search_step(trn_imgs, trn_labels, val_imgs, val_labels, tf_tau)
|
||||
genotype = model.genotype()
|
||||
genotype = CellStructure(genotype)
|
||||
|
||||
#for test_images, test_labels in test_ds:
|
||||
# test_step(test_images, test_labels)
|
||||
|
||||
cur_lr = float(tf.keras.backend.get_value(w_optimizer.lr))
|
||||
template = '{:} Epoch {:03d}/{:03d}, Train-Loss: {:.3f}, Train-Accuracy: {:.2f}%, Valid-Loss: {:.3f}, Valid-Accuracy: {:.2f}% | tau={:.3f} | lr={:.6f}'
|
||||
print(template.format(time_string(), epoch+1, xargs.epochs,
|
||||
train_loss.result(),
|
||||
train_accuracy.result()*100,
|
||||
valid_loss.result(),
|
||||
valid_accuracy.result()*100,
|
||||
cur_tau,
|
||||
cur_lr))
|
||||
print('{:} genotype : {:}\n{:}\n'.format(time_string(), genotype, model.get_np_alphas()))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='NAS-Bench-201', formatter_class=argparse.ArgumentDefaultsHelpFormatter)
|
||||
# training details
|
||||
parser.add_argument('--epochs' , type=int , default= 250 , help='')
|
||||
parser.add_argument('--tau_max' , type=float, default= 10 , help='')
|
||||
parser.add_argument('--tau_min' , type=float, default= 0.1 , help='')
|
||||
parser.add_argument('--w_lr_max' , type=float, default= 0.025, help='')
|
||||
parser.add_argument('--w_lr_min' , type=float, default= 0.001, help='')
|
||||
parser.add_argument('--w_weight_decay' , type=float, default=0.0005, help='')
|
||||
parser.add_argument('--w_momentum' , type=float, default= 0.9 , help='')
|
||||
parser.add_argument('--arch_learning_rate', type=float, default=0.0003, help='')
|
||||
parser.add_argument('--arch_weight_decay' , type=float, default=0.001, help='')
|
||||
# marco structure
|
||||
parser.add_argument('--channel' , type=int , default=16, help='')
|
||||
parser.add_argument('--num_cells' , type=int , default= 5, help='')
|
||||
parser.add_argument('--max_nodes' , type=int , default= 4, help='')
|
||||
args = parser.parse_args()
|
||||
main( args )
|
||||
@@ -1,46 +0,0 @@
|
||||
import os, sys, math, time, random, argparse
|
||||
import tensorflow as tf
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def test_a():
|
||||
x = tf.Variable([[1.], [2.], [4.0]])
|
||||
with tf.GradientTape(persistent=True) as g:
|
||||
trn = tf.math.exp(tf.math.reduce_sum(x))
|
||||
val = tf.math.cos(tf.math.reduce_sum(x))
|
||||
dT_dx = g.gradient(trn, x)
|
||||
dV_dx = g.gradient(val, x)
|
||||
hess_vector = g.gradient(dT_dx, x, output_gradients=dV_dx)
|
||||
print ('calculate ok : {:}'.format(hess_vector))
|
||||
|
||||
def test_b():
|
||||
cce = tf.keras.losses.SparseCategoricalCrossentropy()
|
||||
L1 = tf.convert_to_tensor([0, 1, 2])
|
||||
L2 = tf.convert_to_tensor([2, 0, 1])
|
||||
B = tf.Variable([[.9, .05, .05], [.5, .89, .6], [.05, .01, .94]])
|
||||
with tf.GradientTape(persistent=True) as g:
|
||||
trn = cce(L1, B)
|
||||
val = cce(L2, B)
|
||||
dT_dx = g.gradient(trn, B)
|
||||
dV_dx = g.gradient(val, B)
|
||||
hess_vector = g.gradient(dT_dx, B, output_gradients=dV_dx)
|
||||
print ('calculate ok : {:}'.format(hess_vector))
|
||||
|
||||
def test_c():
|
||||
cce = tf.keras.losses.CategoricalCrossentropy()
|
||||
L1 = tf.convert_to_tensor([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]])
|
||||
L2 = tf.convert_to_tensor([[0., 0., 1.], [0., 1., 0.], [1., 0., 0.]])
|
||||
B = tf.Variable([[.9, .05, .05], [.5, .89, .6], [.05, .01, .94]])
|
||||
with tf.GradientTape(persistent=True) as g:
|
||||
trn = cce(L1, B)
|
||||
val = cce(L2, B)
|
||||
dT_dx = g.gradient(trn, B)
|
||||
dV_dx = g.gradient(val, B)
|
||||
hess_vector = g.gradient(dT_dx, B, output_gradients=dV_dx)
|
||||
print ('calculate ok : {:}'.format(hess_vector))
|
||||
|
||||
if __name__ == '__main__':
|
||||
print(tf.__version__)
|
||||
test_c()
|
||||
#test_b()
|
||||
#test_a()
|
||||
@@ -94,11 +94,11 @@ def visualize_sss_info(api, dataset, vis_save_dir):
|
||||
params.append(info['params'])
|
||||
flops.append(info['flops'])
|
||||
# accuracy
|
||||
info = api.get_more_info(index, dataset, hp='90')
|
||||
info = api.get_more_info(index, dataset, hp='90', is_random=False)
|
||||
train_accs.append(info['train-accuracy'])
|
||||
test_accs.append(info['test-accuracy'])
|
||||
if dataset == 'cifar10':
|
||||
info = api.get_more_info(index, 'cifar10-valid', hp='90')
|
||||
info = api.get_more_info(index, 'cifar10-valid', hp='90', is_random=False)
|
||||
valid_accs.append(info['valid-accuracy'])
|
||||
else:
|
||||
valid_accs.append(info['valid-accuracy'])
|
||||
@@ -182,11 +182,11 @@ def visualize_tss_info(api, dataset, vis_save_dir):
|
||||
params.append(info['params'])
|
||||
flops.append(info['flops'])
|
||||
# accuracy
|
||||
info = api.get_more_info(index, dataset, hp='200')
|
||||
info = api.get_more_info(index, dataset, hp='200', is_random=False)
|
||||
train_accs.append(info['train-accuracy'])
|
||||
test_accs.append(info['test-accuracy'])
|
||||
if dataset == 'cifar10':
|
||||
info = api.get_more_info(index, 'cifar10-valid', hp='200')
|
||||
info = api.get_more_info(index, 'cifar10-valid', hp='200', is_random=False)
|
||||
valid_accs.append(info['valid-accuracy'])
|
||||
else:
|
||||
valid_accs.append(info['valid-accuracy'])
|
||||
@@ -319,6 +319,68 @@ def visualize_rank_info(api, vis_save_dir, indicator):
|
||||
plt.close('all')
|
||||
|
||||
|
||||
def calculate_correlation(*vectors):
|
||||
matrix = []
|
||||
for i, vectori in enumerate(vectors):
|
||||
x = []
|
||||
for j, vectorj in enumerate(vectors):
|
||||
x.append( np.corrcoef(vectori, vectorj)[0,1] )
|
||||
matrix.append( x )
|
||||
return np.array(matrix)
|
||||
|
||||
|
||||
def visualize_all_rank_info(api, vis_save_dir, indicator):
|
||||
vis_save_dir = vis_save_dir.resolve()
|
||||
# print ('{:} start to visualize {:} information'.format(time_string(), api))
|
||||
vis_save_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
cifar010_cache_path = vis_save_dir / '{:}-cache-{:}-info.pth'.format('cifar10', indicator)
|
||||
cifar100_cache_path = vis_save_dir / '{:}-cache-{:}-info.pth'.format('cifar100', indicator)
|
||||
imagenet_cache_path = vis_save_dir / '{:}-cache-{:}-info.pth'.format('ImageNet16-120', indicator)
|
||||
cifar010_info = torch.load(cifar010_cache_path)
|
||||
cifar100_info = torch.load(cifar100_cache_path)
|
||||
imagenet_info = torch.load(imagenet_cache_path)
|
||||
indexes = list(range(len(cifar010_info['params'])))
|
||||
|
||||
print ('{:} start to visualize relative ranking'.format(time_string()))
|
||||
|
||||
|
||||
dpi, width, height = 250, 3200, 1400
|
||||
figsize = width / float(dpi), height / float(dpi)
|
||||
LabelSize, LegendFontsize = 14, 14
|
||||
|
||||
fig, axs = plt.subplots(1, 2, figsize=figsize)
|
||||
ax1, ax2 = axs
|
||||
|
||||
sns_size = 15
|
||||
CoRelMatrix = calculate_correlation(cifar010_info['valid_accs'], cifar010_info['test_accs'], cifar100_info['valid_accs'], cifar100_info['test_accs'], imagenet_info['valid_accs'], imagenet_info['test_accs'])
|
||||
|
||||
sns.heatmap(CoRelMatrix, annot=True, annot_kws={'size':sns_size}, fmt='.3f', linewidths=0.5, ax=ax1,
|
||||
xticklabels=['C10-V', 'C10-T', 'C100-V', 'C100-T', 'I120-V', 'I120-T'],
|
||||
yticklabels=['C10-V', 'C10-T', 'C100-V', 'C100-T', 'I120-V', 'I120-T'])
|
||||
|
||||
selected_indexes, acc_bar = [], 92
|
||||
for i, acc in enumerate(cifar010_info['test_accs']):
|
||||
if acc > acc_bar: selected_indexes.append( i )
|
||||
cifar010_valid_accs = np.array(cifar010_info['valid_accs'])[ selected_indexes ]
|
||||
cifar010_test_accs = np.array(cifar010_info['test_accs']) [ selected_indexes ]
|
||||
cifar100_valid_accs = np.array(cifar100_info['valid_accs'])[ selected_indexes ]
|
||||
cifar100_test_accs = np.array(cifar100_info['test_accs']) [ selected_indexes ]
|
||||
imagenet_valid_accs = np.array(imagenet_info['valid_accs'])[ selected_indexes ]
|
||||
imagenet_test_accs = np.array(imagenet_info['test_accs']) [ selected_indexes ]
|
||||
CoRelMatrix = calculate_correlation(cifar010_valid_accs, cifar010_test_accs, cifar100_valid_accs, cifar100_test_accs, imagenet_valid_accs, imagenet_test_accs)
|
||||
|
||||
sns.heatmap(CoRelMatrix, annot=True, annot_kws={'size':sns_size}, fmt='.3f', linewidths=0.5, ax=ax2,
|
||||
xticklabels=['C10-V', 'C10-T', 'C100-V', 'C100-T', 'I120-V', 'I120-T'],
|
||||
yticklabels=['C10-V', 'C10-T', 'C100-V', 'C100-T', 'I120-V', 'I120-T'])
|
||||
ax1.set_title('Correlation coefficient over ALL candidates')
|
||||
ax2.set_title('Correlation coefficient over candidates with accuracy > {:}%'.format(acc_bar))
|
||||
save_path = (vis_save_dir / '{:}-all-relative-rank.png'.format(indicator)).resolve()
|
||||
fig.savefig(save_path, dpi=dpi, bbox_inches='tight', format='png')
|
||||
print ('{:} save into {:}'.format(time_string(), save_path))
|
||||
plt.close('all')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='NAS-Bench-X', formatter_class=argparse.ArgumentDefaultsHelpFormatter)
|
||||
parser.add_argument('--save_dir', type=str, default='output/NAS-BENCH-202', help='Folder to save checkpoints and log.')
|
||||
@@ -326,20 +388,19 @@ if __name__ == '__main__':
|
||||
# use for train the model
|
||||
args = parser.parse_args()
|
||||
|
||||
visualize_rank_info(None, Path('output/vis-nas-bench/'), 'tss')
|
||||
visualize_rank_info(None, Path('output/vis-nas-bench/'), 'sss')
|
||||
|
||||
datasets = ['cifar10', 'cifar100', 'ImageNet16-120']
|
||||
api201 = NASBench201API(None, verbose=True)
|
||||
visualize_tss_info(api201, 'cifar10', Path('output/vis-nas-bench'))
|
||||
visualize_tss_info(api201, 'cifar100', Path('output/vis-nas-bench'))
|
||||
visualize_tss_info(api201, 'ImageNet16-120', Path('output/vis-nas-bench'))
|
||||
for xdata in datasets:
|
||||
visualize_tss_info(api201, xdata, Path('output/vis-nas-bench'))
|
||||
|
||||
api301 = NASBench301API(None, verbose=True)
|
||||
visualize_sss_info(api301, 'cifar10', Path('output/vis-nas-bench'))
|
||||
visualize_sss_info(api301, 'cifar100', Path('output/vis-nas-bench'))
|
||||
visualize_sss_info(api301, 'ImageNet16-120', Path('output/vis-nas-bench'))
|
||||
for xdata in datasets:
|
||||
visualize_sss_info(api301, xdata, Path('output/vis-nas-bench'))
|
||||
|
||||
visualize_info(None, Path('output/vis-nas-bench/'), 'tss')
|
||||
visualize_info(None, Path('output/vis-nas-bench/'), 'sss')
|
||||
visualize_rank_info(None, Path('output/vis-nas-bench/'), 'tss')
|
||||
visualize_rank_info(None, Path('output/vis-nas-bench/'), 'sss')
|
||||
|
||||
visualize_all_rank_info(None, Path('output/vis-nas-bench/'), 'tss')
|
||||
visualize_all_rank_info(None, Path('output/vis-nas-bench/'), 'sss')
|
||||
|
||||
Reference in New Issue
Block a user