def main():
# Parse the JSON arguments
try:
config_args = parse_args()
except:
print("Add a config file using \'--config file_name.json\'")
exit(1)
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
# Reset the default Tensorflow graph
tf.reset_default_graph()
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# Data loading
# The batch size is equal to 1 when testing to simulate the real experiment.
data_batch_size = config_args.batch_size if config_args.train_or_test == "train" else 1
data = DataLoader(data_batch_size, config_args.shuffle)
print("Loading Data...")
config_args.img_height, config_args.img_width, config_args.num_channels, \
config_args.train_data_size, config_args.test_data_size = data.load_data()
print("Data loaded\n\n")
# Model creation
print("Building the model...")
model = ShuffleNet(config_args)
print("Model is built successfully\n\n")
# Summarizer creation
summarizer = Summarizer(sess, config_args.summary_dir)
# Train class
trainer = Train(sess, model, data, summarizer)
if config_args.train_or_test == 'train':
try:
print("FLOPs for batch size = " + str(config_args.batch_size) +
"\n")
calculate_flops()
print("Training...")
trainer.train()
print("Training Finished\n\n")
except KeyboardInterrupt:
trainer.save_model()
elif config_args.train_or_test == 'test':
print("FLOPs for single inference \n")
calculate_flops()
# This can be 'val' or 'test' or even 'train' according to the needs.
print("Testing...")
trainer.test('val')
print("Testing Finished\n\n")
else:
raise ValueError("Train or Test options only are allowed")
def main():
# Parse the JSON arguments
config_args = parse_args()
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
model = MobileNetV2(config_args)
if config_args.cuda:
model.cuda()
cudnn.enabled = True
cudnn.benchmark = True
print("Loading Data...")
data = BenchPressData(config_args)
print("Data loaded successfully\n")
trainer = Train(model, data.trainloader, data.testloader, config_args)
if config_args.to_train:
try:
print("Training...")
trainer.train()
print("Training Finished\n")
except KeyboardInterrupt:
pass
if config_args.to_test:
print("Testing...")
trainer.test(data.testloader)
print("Testing Finished\n")
def main():
# Parse the JSON arguments
config_args = parse_args()
# Create the experiment directories
experiment_dir, summary_dir, checkpoint_dir, output_dir = create_experiment_dirs(
config_args.experiment_dir)
generator = Generator(config_args.Z_dim, config_args.dim_multiplier, config_args.img_channels)
discriminator = Discriminator(config_args.dim_multiplier, config_args.img_channels, config_args.leaky)
data_loader = CelebADataLoader(config_args)
try:
device = torch.device(config_args.device)
except:
print("Error in choosing your running device \"{}\". Using CPU instead.\n".format(config_args.device))
device = torch.device('cpu')
trainer = DCGANTrainer(generator, discriminator, data_loader, device, summary_dir, checkpoint_dir, output_dir,
config_args)
if config_args.mode == "train":
trainer.train()
else:
raise ValueError("Choose from the following modes: (train)")
def main():
# Parse the JSON arguments
config_args = parse_args()
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(config_args.experiment_dir)
# Reset the default Tensorflow graph
tf.reset_default_graph()
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# Data loading
# The batch size is equal to 1 when testing to simulate the real experiment.
data_batch_size = config_args.batch_size if config_args.train_or_test == "train" else 1
data = DataLoader(data_batch_size, config_args.shuffle)
print("Loading Data...")
config_args.img_height, config_args.img_width, config_args.num_channels, \
config_args.train_data_size, config_args.test_data_size = data.load_data()
print("Data loaded\n\n")
# Model creation
print("Building the model...")
model = ShuffleNet(config_args)
print("Model is built successfully\n\n")
# Parameters visualization
show_parameters()
# Summarizer creation
summarizer = Summarizer(sess, config_args.summary_dir)
# Train class
trainer = Train(sess, model, data, summarizer)
if config_args.train_or_test == 'train':
try:
# print("FLOPs for batch size = " + str(config_args.batch_size) + "\n")
# calculate_flops()
print("Training...")
trainer.train()
print("Training Finished\n\n")
except KeyboardInterrupt:
trainer.save_model()
elif config_args.train_or_test == 'test':
# print("FLOPs for single inference \n")
# calculate_flops()
# This can be 'val' or 'test' or even 'train' according to the needs.
print("Testing...")
trainer.test('val')
print("Testing Finished\n\n")
else:
raise ValueError("Train or Test options only are allowed")
def main():
# Parse the JSON arguments
try:
config_args = parse_args()
except:
print("Add a config file using \'--config file_name.json\'")
exit(1)
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
# Reset the default Tensorflow graph
tf.reset_default_graph()
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# Data loading
data = DataLoader(config_args.batch_size, config_args.shuffle)
print("Loading Data...")
config_args.img_height, config_args.img_width, config_args.num_channels, \
config_args.train_data_size, config_args.test_data_size = data.load_data()
print("Data loaded\n\n")
# Model creation
print("Building the model...")
model = MobileNet(config_args)
print("Model is built successfully\n\n")
# Summarizer creation
summarizer = Summarizer(sess, config_args.summary_dir)
# Train class
trainer = Train(sess, model, data, summarizer)
if config_args.to_train:
try:
print("Training...")
trainer.train()
print("Training Finished\n\n")
except KeyboardInterrupt:
trainer.save_model()
if config_args.to_test:
print("Final test!")
ans_list = trainer.test('val')
# ans_list = trainer.test('train')
# print(len(ans_list))
# print(ans_list)
print("Testing Finished\n\n")
def main(img):
config = 'config/test2.json'
with open(config, 'r') as config_file:
config_args_dict = json.load(config_file)
config_args = edict(config_args_dict)
print(config_args)
print("\n")
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
# Reset the default Tensorflow graph
tf.reset_default_graph()
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# Data loading
data = DataLoader(config_args.batch_size, config_args.shuffle, img)
print("Loading Data...")
config_args.img_height, config_args.img_width, config_args.num_channels, \
config_args.train_data_size, config_args.test_data_size = data.load_data()
print("Data loaded\n\n")
# Model creation
print("Building the model...")
model = MobileNet(config_args)
print("Model is built successfully\n\n")
# Summarizer creation
summarizer = Summarizer(sess, config_args.summary_dir)
# Train class
trainer = Train(sess, model, data, summarizer)
print("Final test!")
ans_list = trainer.test('val')
# ans_list = trainer.test('train')
# print(len(ans_list))
print(ans_list)
print("Testing Finished\n\n")
# except KeyboardInterrupt:
# trainer.save_model()
# if config_args.to_test:
# print("Final test!")
# trainer.test('val')
# print("Testing Finished\n\n")
# trainer.dectect(FaceCropper().generate('fake.png'))
if __name__ == '__main__':
# main()
config_args = parse_args()
config_args.img_height, config_args.img_width, config_args.num_channels = (
224, 224, 3)
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
faces = FaceCropper().generate('maxresdefault.jpg')
with tf.Session(config=config) as sess:
config_args.batch_size = len(faces)
model = MobileNet(config_args)
sess.run(
tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer()))
saver = tf.train.Saver(max_to_keep=config_args.max_to_keep,
keep_checkpoint_every_n_hours=10,
save_relative_paths=True)
saver.restore(sess,
tf.train.latest_checkpoint(config_args.checkpoint_dir))
def main():
# Parse the JSON arguments
try:
config_args = parse_args()
except:
print("Add a config file using \'--config file_name.json\'")
exit(1)
# Create the experiment directories
_, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
config_args.experiment_dir)
# Reset the default Tensorflow graph
tf.reset_default_graph()
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# Data loading
data = DataLoader(config_args.batch_size, config_args.shuffle)
print("Loading Data...")
config_args.img_height, config_args.img_width, config_args.num_channels, \
config_args.train_data_size, config_args.test_data_size = data.load_data()
print("Data loaded\n\n")
# Model creation
print("Building the model...")
if config_args.quantize == True:
print('Quantized model created')
# Quantized model creation
activation_quantizer = linear_mid_tread_half_quantizer
activation_quantizer_kwargs = {'bit': 2, 'max_value': 2}
weight_quantizer = binary_mean_scaling_quantizer
weight_quantizer_kwargs = {}
model = MobileNetQuantize(
config_args,
activation_quantizer=activation_quantizer,
activation_quantizer_kwargs=activation_quantizer_kwargs,
weight_quantizer=weight_quantizer,
weight_quantizer_kwargs=weight_quantizer_kwargs)
else:
print('Full precision model created')
model = MobileNet(config_args)
print("Model is built successfully\n\n")
# Summarizer creation
summarizer = Summarizer(sess, config_args.summary_dir)
# Train class
trainer = Train(sess, model, data, summarizer)
if config_args.to_train:
try:
print("Training...")
trainer.train()
print("Training Finished\n\n")
except KeyboardInterrupt:
trainer.save_model()
if config_args.to_test:
print("Final test!")
trainer.test('val')
print("Testing Finished\n\n")
