# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'MUNIT':
trainer = MUNIT_Trainer(config)
elif opts.trainer == 'UNIT':
trainer = UNIT_Trainer(config)
else:
sys.exit("Only support MUNIT|UNIT")
trainer.cuda()
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config)
train_display_images_a = torch.stack(
[train_loader_a.dataset[i] for i in range(display_size)]).cuda()
train_display_images_b = torch.stack(
[train_loader_b.dataset[i] for i in range(display_size)]).cuda()
test_display_images_a = torch.stack(
[test_loader_a.dataset[i] for i in range(display_size)]).cuda()
test_display_images_b = torch.stack(
[test_loader_b.dataset[i] for i in range(display_size)]).cuda()
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(
os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--config',
type=str,
default='configs/edges2handbags_folder.yaml',
help='Path to the config file.')
parser.add_argument('--output_path',
type=str,
default='.',
help="outputs path")
#resume option => [, default='730000']
parser.add_argument("--resume", default='150000', action="store_true")
parser.add_argument('--trainer',
type=str,
default='MUNIT',
help="MUNIT|UNIT")
opts = parser.parse_args()
cudnn.benchmark = True
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'MUNIT':
trainer = MUNIT_Trainer(config)
elif opts.trainer == 'UNIT':
trainer = UNIT_Trainer(config)
else:
sys.exit("Only support MUNIT|UNIT")
trainer.cuda()
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config)
train_display_images_a = torch.stack(
[train_loader_a.dataset[i] for i in range(display_size)]).cuda()
train_display_images_b = torch.stack(
[train_loader_b.dataset[i] for i in range(display_size)]).cuda()
test_display_images_a = torch.stack(
[test_loader_a.dataset[i] for i in range(display_size)]).cuda()
test_display_images_b = torch.stack(
[test_loader_b.dataset[i] for i in range(display_size)]).cuda()
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(
os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
output_directory)
shutil.copy(opts.config, os.path.join(
output_directory, 'config.yaml')) # copy config file to output folder
# Start training
iterations = trainer.resume(checkpoint_directory,
hyperparameters=config) if opts.resume else 0
while True:
for it, (images_a,
images_b) in enumerate(zip(train_loader_a, train_loader_b)):
trainer.update_learning_rate()
images_a, images_b = images_a.cuda().detach(), images_b.cuda(
).detach()
with Timer("Elapsed time in update: %f"):
# Main training code
trainer.dis_update(images_a, images_b, config)
trainer.gen_update(images_a, images_b, config)
torch.cuda.synchronize()
# Dump training stats in log file
if (iterations + 1) % config['log_iter'] == 0:
print("Iteration: %08d/%08d" % (iterations + 1, max_iter))
write_loss(iterations, trainer, train_writer)
# Write images
if (iterations + 1) % config['image_save_iter'] == 0:
with torch.no_grad():
test_image_outputs = trainer.sample(
test_display_images_a, test_display_images_b)
train_image_outputs = trainer.sample(
train_display_images_a, train_display_images_b)
write_2images(test_image_outputs, display_size,
image_directory, 'test_%08d' % (iterations + 1))
write_2images(train_image_outputs, display_size,
image_directory, 'train_%08d' % (iterations + 1))
# HTML
write_html(output_directory + "/index.html", iterations + 1,
config['image_save_iter'], 'images')
if (iterations + 1) % config['image_display_iter'] == 0:
with torch.no_grad():
image_outputs = trainer.sample(train_display_images_a,
train_display_images_b)
write_2images(image_outputs, display_size, image_directory,
'train_current')
# Save network weights
if (iterations + 1) % config['snapshot_save_iter'] == 0:
trainer.save(checkpoint_directory, iterations)
iterations += 1
if iterations >= max_iter:
sys.exit('Finish training')
def main(argv):
(opts, args) = parser.parse_args(argv)
cudnn.benchmark = True
model_name = os.path.splitext(os.path.basename(opts.config))[0]
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
# Setup model and data loader
trainer = MUNIT_Trainer(config)
trainer.cuda()
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config)
test_display_images_a = Variable(torch.stack(
[test_loader_a.dataset[i] for i in range(display_size)]).cuda(),
volatile=True)
test_display_images_b = Variable(torch.stack(
[test_loader_b.dataset[i] for i in range(display_size)]).cuda(),
volatile=True)
train_display_images_a = Variable(torch.stack(
[train_loader_a.dataset[i] for i in range(display_size)]).cuda(),
volatile=True)
train_display_images_b = Variable(torch.stack(
[train_loader_b.dataset[i] for i in range(display_size)]).cuda(),
volatile=True)
# Setup logger and output folders
train_writer = tensorboard.SummaryWriter(os.path.join(
opts.log, model_name))
output_directory = os.path.join(opts.outputs, model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
output_directory)
shutil.copy(opts.config, os.path.join(
output_directory, 'config.yaml')) # copy config file to output folder
# Start training
iterations = trainer.resume(checkpoint_directory) if opts.resume else 0
while True:
for it, (images_a,
images_b) in enumerate(izip(train_loader_a, train_loader_b)):
trainer.update_learning_rate()
images_a, images_b = Variable(images_a.cuda()), Variable(
images_b.cuda())
# Main training code
trainer.dis_update(images_a, images_b, config)
trainer.gen_update(images_a, images_b, config)
# Dump training stats in log file
if (iterations + 1) % config['log_iter'] == 0:
print("Iteration: %08d/%08d" % (iterations + 1, max_iter))
write_loss(iterations, trainer, train_writer)
# Write images
if (iterations + 1) % config['image_save_iter'] == 0:
# Test set images
image_outputs = trainer.sample(test_display_images_a,
test_display_images_b)
write_images(
image_outputs, display_size,
'%s/gen_test%08d.jpg' % (image_directory, iterations + 1))
# Train set images
image_outputs = trainer.sample(train_display_images_a,
train_display_images_b)
write_images(
image_outputs, display_size,
'%s/gen_train%08d.jpg' % (image_directory, iterations + 1))
# HTML
write_html(output_directory + "/index.html", iterations + 1,
config['image_save_iter'], 'images')
if (iterations + 1) % config['image_save_iter'] == 0:
image_outputs = trainer.sample(test_display_images_a,
test_display_images_b)
write_images(image_outputs, display_size,
'%s/gen.jpg' % image_directory)
# Save network weights
if (iterations + 1) % config['snapshot_save_iter'] == 0:
trainer.save(checkpoint_directory, iterations)
iterations += 1
if iterations >= max_iter:
return
sys.exit("Only support MUNIT|UNIT.")
os.exit()
trainer.cuda()
dataset_letters = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I']
samples = list()
dataset_probs = list()
augmentation = list()
for i in range(config['n_datasets']):
samples.append(config['sample_' + dataset_letters[i]])
dataset_probs.append(config['prob_' + dataset_letters[i]])
augmentation.append(config['transform_' + dataset_letters[i]])
_, test_loader_list = get_all_data_loaders(config, config['n_datasets'],
samples, augmentation,
config['trim'])
# Setup logger and output folders.
model_name = os.path.splitext(os.path.basename(opts.config))[0]
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(output_directory)
shutil.copy(opts.config,
os.path.join(output_directory,
'config.yaml')) # Copy config file to output folder.
# Creating isomorphic directory.
if not os.path.exists(os.path.join(image_directory, 'isomorphic')):
os.mkdir(os.path.join(image_directory, 'isomorphic'))
# Start test.
# Load experiment setting
if opts.resume:
config = get_config('./outputs/' + opts.name + '/config.yaml')
else:
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'DGNet':
trainer = DGNet_Trainer(config, gpu_ids) # from trainer ->DGNet_Trainer
trainer.cuda()
random.seed(7) #fix random result
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config) # function from utils.py
# 随机选出一些图片，然后根据选出的任意两张id不同的图片，输出一些训练过程中产生的重构图片或合成图片。
train_a_rand = random.permutation(
train_loader_a.dataset.img_num)[0:display_size]
train_b_rand = random.permutation(
train_loader_b.dataset.img_num)[0:display_size]
test_a_rand = random.permutation(test_loader_a.dataset.img_num)[0:display_size]
test_b_rand = random.permutation(test_loader_b.dataset.img_num)[0:display_size]
train_display_images_a = torch.stack(
[train_loader_a.dataset[i][0] for i in train_a_rand]).cuda()
train_display_images_ap = torch.stack(
[train_loader_a.dataset[i][2] for i in train_a_rand]).cuda()
train_display_images_b = torch.stack(
default='.',
help="outputs path")
parser.add_argument("--resume", action="store_true")
opts = parser.parse_args()
cudnn.benchmark = True
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
# Setup model and data loader
trainer = Trainer(config)
# trainer.cuda()
(train_loader_a, train_loader_b, test_loader_a,
test_loader_b) = get_all_data_loaders(config)
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(
os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(output_directory)
# copy config file to output folder
shutil.copy(opts.config, os.path.join(output_directory, 'config.yaml'))
# Start training
iterations = trainer.resume(checkpoint_directory,
hyperparameters=config) if opts.resume else 0
while True:
it = 0
if opts.a2b==1:
new_size = config['new_size_a']
else:
new_size = config['new_size_b']
start = time.time()
n_rand = 3
if opts.trainer == 'SECUNIT' or opts.trainer == 'CDUNIT':
trainer.resume(opts.checkpoint, hyperparameters=config)
trainer.cuda()
trainer.eval()
config['batch_size'] = 8
img_count_a, img_count_b = 0, 0
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(config, train_bool=False)
base_dir = Path(opts.output_folder)
orig_dir = Path(base_dir, "orig")
orig_dir.mkdir(parents=True, exist_ok=True)
tran_dir = Path(base_dir, "fake")
tran_dir.mkdir(exist_ok=True)
seg_dir = Path(base_dir, "seg")
seg_dir.mkdir(exist_ok=True)
style_dir = Path(base_dir, "style")
style_dir.mkdir(exist_ok=True)
with torch.no_grad():
img_count_a, img_count_b = enum_loader(train_loader_a, train_loader_b, orig_dir, tran_dir, seg_dir, style_dir, opts, img_count_a, img_count_b, n_rand)
img_count_a, img_count_b = enum_loader(test_loader_a, test_loader_b, orig_dir, tran_dir, seg_dir, style_dir, opts, img_count_a, img_count_b, n_rand)
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'IMPNet':
trainer = IPMNet_Trainer(config)
trainer.cuda()
random.seed(7) # fix random result
train_loader_a, train_loader_b, test_loader_a, test_loader_b, train_mask_loader_a, train_mask_loader_b,\
test_mask_loader_a, test_mask_loader_b, train_texture_loader_a, train_texture_loader_b,test_texture_loader_a,\
test_texture_loader_b = get_all_data_loaders(config)
train_a_rand = random.permutation(len(train_loader_a.dataset))[0:display_size]
train_b_rand = random.permutation(len(train_loader_b.dataset))[0:display_size]
test_a_rand = random.permutation(len(test_loader_a.dataset))[0:display_size]
test_b_rand = random.permutation(len(test_loader_b.dataset))[0:display_size]
train_display_images_a = torch.stack(
[train_loader_a.dataset[i] for i in train_a_rand]).cuda()
train_display_mask_a = torch.stack(
[train_mask_loader_a.dataset[i] for i in train_a_rand]).cuda()
train_display_texture_a = torch.stack(
[train_texture_loader_a.dataset[i] for i in train_a_rand]).cuda()
train_display_images_a, train_display_mask_a, train_display_texture_a = randomcrop(
train_display_images_a, train_display_mask_a, train_display_texture_a,
config['crop_image_height'], config['crop_image_width'])
def main():
cudnn.benchmark = True
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
trainer = UNIT_Trainer(config)
if torch.cuda.is_available():
trainer.cuda(config['gpuID'])
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config)
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
writer = SummaryWriter(os.path.join(opts.output_path + "/logs",
model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
output_directory)
shutil.copy(opts.config, os.path.join(
output_directory, 'config.yaml')) # copy config file to output folder
print('start training !!')
# Start training
iterations = trainer.resume(checkpoint_directory,
hyperparameters=config) if opts.resume else 0
TraindataA = data_prefetcher(train_loader_a)
TraindataB = data_prefetcher(train_loader_b)
testdataA = data_prefetcher(test_loader_a)
testdataB = data_prefetcher(test_loader_b)
while True:
dataA = TraindataA.next()
dataB = TraindataB.next()
if dataA is None or dataB is None:
TraindataA = data_prefetcher(train_loader_a)
TraindataB = data_prefetcher(train_loader_b)
dataA = TraindataA.next()
dataB = TraindataB.next()
with Timer("Elapsed time in update: %f"):
# Main training code
for _ in range(3):
trainer.content_update(dataA, dataB, config)
trainer.dis_update(dataA, dataB, config)
trainer.gen_update(dataA, dataB, config)
# torch.cuda.synchronize()
trainer.update_learning_rate()
# Dump training stats in log file
if (iterations + 1) % config['log_iter'] == 0:
print("Iteration: %08d/%08d" % (iterations + 1, max_iter))
write_loss(iterations, trainer, writer)
if (iterations + 1) % config['image_save_iter'] == 0:
testa = testdataA.next()
testb = testdataB.next()
if dataA is None or dataB is None or dataA.size(
0) != display_size or dataB.size(0) != display_size:
testdataA = data_prefetcher(test_loader_a)
testdataB = data_prefetcher(test_loader_b)
testa = testdataA.next()
testb = testdataB.next()
with torch.no_grad():
test_image_outputs = trainer.sample(testa, testb)
train_image_outputs = trainer.sample(dataA, dataB)
if test_image_outputs is not None and train_image_outputs is not None:
write_2images(test_image_outputs, display_size,
image_directory, 'test_%08d' % (iterations + 1))
write_2images(train_image_outputs, display_size,
image_directory, 'train_%08d' % (iterations + 1))
# HTML
write_html(output_directory + "/index.html", iterations + 1,
config['image_save_iter'], 'images')
if (iterations + 1) % config['image_display_iter'] == 0:
with torch.no_grad():
image_outputs = trainer.sample(dataA, dataB)
if image_outputs is not None:
write_2images(image_outputs, display_size, image_directory,
'train_current')
# Save network weights
if (iterations + 1) % config['snapshot_save_iter'] == 0:
trainer.save(checkpoint_directory, iterations)
iterations += 1
if iterations >= max_iter:
writer.close()
sys.exit('Finish training')
parser.add_argument("--resume", action="store_true")
opts = parser.parse_args()
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_lize = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
trainer = AGUIT_Trainer(config)
trainer.cuda()
# load labeled and unlabeled dataloaders
train_loader_l, train_loader_u = get_all_data_loaders(config)
test_display_images_l = [
torch.stack([train_loader_l.dataset[i][0]
for i in range(display_lize)]).cuda(),
torch.stack([train_loader_l.dataset[i][1]
for i in range(display_lize)]).cuda()
]
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(
os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(output_directory)
shutil.copy(opts.config,
trainer = MUNIT_Trainer(config,
resume_epoch=opts.load,
snapshot_dir=opts.snapshot_dir)
trainer.cuda()
dataset_letters = eval(opts.dataset_letters)
samples = list()
dataset_probs = list()
augmentation = list()
for i in range(config['n_datasets']):
samples.append(config['sample_' + dataset_letters[i]])
dataset_probs.append(config['prob_' + dataset_letters[i]])
augmentation.append(config['transform_' + dataset_letters[i]])
train_loader_list, test_loader_list = get_all_data_loaders(
config, config['n_datasets'], samples, augmentation, config['trim'],
opts.dataset_letters)
# Setup logger and output folders.
model_name = os.path.splitext(os.path.basename(opts.config))[0]
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(output_directory)
shutil.copy(opts.config,
os.path.join(output_directory,
'config.yaml')) # Copy config file to output folder.
# Creating isomorphic directory.
if not os.path.exists(os.path.join(image_directory, 'isomorphic')):
os.mkdir(os.path.join(image_directory, 'isomorphic'))
# Start test.
def main():
from utils import get_all_data_loaders, prepare_sub_folder, write_html, write_loss, get_config, write_2images, Timer
import argparse
from torch.autograd import Variable
from trainer import MUNIT_Trainer, UNIT_Trainer
import torch.backends.cudnn as cudnn
import torch
# try:
# from itertools import izip as zip
# except ImportError: # will be 3.x series
# pass
import os
import sys
import tensorboardX
import shutil
os.environ["CUDA_VISIBLE_DEVICES"] = str(0)
parser = argparse.ArgumentParser()
parser.add_argument('--config',
type=str,
default='configs/edges2handbags_folder.yaml',
help='Path to the config file.')
parser.add_argument('--output_path',
type=str,
default='.',
help="outputs path")
parser.add_argument("--resume", action="store_true")
parser.add_argument('--trainer',
type=str,
default='MUNIT',
help="MUNIT|UNIT")
opts = parser.parse_args()
cudnn.benchmark = True
'''
Note: https://www.pytorchtutorial.com/when-should-we-set-cudnn-benchmark-to-true/
大部分情况下，设置这个 flag 可以让内置的 cuDNN 的 auto-tuner 自动寻找最适合当前配置的高效算法，来达到优化运行效率的问题
1. 如果网络的输入数据维度或类型上变化不大，设置 torch.backends.cudnn.benchmark = true 可以增加运行效率；
2. 如果网络的输入数据在每次 iteration 都变化的话，会导致 cnDNN 每次都会去寻找一遍最优配置，这样反而会降低运行效率。
'''
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'MUNIT':
trainer = MUNIT_Trainer(config)
elif opts.trainer == 'UNIT':
trainer = UNIT_Trainer(config)
else:
sys.exit("Only support MUNIT|UNIT")
trainer.cuda()
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(
config)
train_display_images_a = torch.stack(
[train_loader_a.dataset[i] for i in range(display_size)]).cuda()
train_display_images_b = torch.stack(
[train_loader_b.dataset[i] for i in range(display_size)]).cuda()
test_display_images_a = torch.stack(
[test_loader_a.dataset[i] for i in range(display_size)]).cuda()
test_display_images_b = torch.stack(
[test_loader_b.dataset[i] for i in range(display_size)]).cuda()
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(
os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
output_directory)
shutil.copy(opts.config, os.path.join(
output_directory, 'config.yaml')) # copy config file to output folder
# Start training
iterations = trainer.resume(checkpoint_directory,
hyperparameters=config) if opts.resume else 0
while True:
for it, (images_a,
images_b) in enumerate(zip(train_loader_a, train_loader_b)):
trainer.update_learning_rate()
images_a, images_b = images_a.cuda().detach(), images_b.cuda(
).detach()
with Timer("Elapsed time in update: %f"):
# Main training code
trainer.dis_update(images_a, images_b, config)
trainer.gen_update(images_a, images_b, config)
torch.cuda.synchronize()
# Dump training stats in log file
if (iterations + 1) % config['log_iter'] == 0:
print("Iteration: %08d/%08d" % (iterations + 1, max_iter))
write_loss(iterations, trainer, train_writer)
# Write images
if (iterations + 1) % config['image_save_iter'] == 0:
with torch.no_grad():
test_image_outputs = trainer.sample(
test_display_images_a, test_display_images_b)
train_image_outputs = trainer.sample(
train_display_images_a, train_display_images_b)
write_2images(test_image_outputs, display_size,
image_directory, 'test_%08d' % (iterations + 1))
write_2images(train_image_outputs, display_size,
image_directory, 'train_%08d' % (iterations + 1))
# HTML
write_html(output_directory + "/index.html", iterations + 1,
config['image_save_iter'], 'images')
if (iterations + 1) % config['image_display_iter'] == 0:
with torch.no_grad():
image_outputs = trainer.sample(train_display_images_a,
train_display_images_b)
write_2images(image_outputs, display_size, image_directory,
'train_current')
# Save network weights
if (iterations + 1) % config['snapshot_save_iter'] == 0:
trainer.save(checkpoint_directory, iterations)
iterations += 1
if iterations >= max_iter:
sys.exit('Finish training')
if __name__ == '__main__':
os.environ['CUDA_VISIBLE_DEVICES'] = '7'
device = torch.device(
'cuda:0') if torch.cuda.is_available() else torch.device('cpu')
# Load config
config = Config().parser.parse_args()
torch.backends.cudnn.benchmark = True
if torch.cuda.is_available():
torch.cuda.manual_seed(config.seed)
torch.manual_seed(config.seed)
max_iter = config.max_iter
display_size = config.display_size
# Achieve data loader
train_loader_a, train_loader_b, _, _ = get_all_data_loaders(config)
train_display_images_a = torch.stack(
[train_loader_a.dataset[i] for i in range(display_size)]).to(device)
train_display_images_b = torch.stack(
[train_loader_b.dataset[i] for i in range(display_size)]).to(device)
# Main models
model = V2VModel(config).to(device)
# Setup logger and output folders
model_name = config.model_name
train_writer = SummaryWriter(config.log_dir)
output_directory = os.path.join(config.output_path + '/outputs',
model_name)
checkpoint_directory, image_directory = prepare_sub_folder(
output_directory)
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
display_size = config['display_size']
config['vgg_model_path'] = opts.output_path
# Setup model and data loader
if opts.trainer == 'MUNIT':
trainer = MUNIT_Trainer(config)
elif opts.trainer == 'UNIT':
trainer = UNIT_Trainer(config)
else:
sys.exit("Only support MUNIT|UNIT")
trainer.cuda()
train_loader_a, train_loader_b, test_loader_a, test_loader_b = get_all_data_loaders(config)
train_display_images_a = Variable(torch.stack([train_loader_a.dataset[i] for i in range(display_size)]).cuda(), volatile=True)
train_display_images_b = Variable(torch.stack([train_loader_b.dataset[i] for i in range(display_size)]).cuda(), volatile=True)
test_display_images_a = Variable(torch.stack([test_loader_a.dataset[i] for i in range(display_size)]).cuda(), volatile=True)
test_display_images_b = Variable(torch.stack([test_loader_b.dataset[i] for i in range(display_size)]).cuda(), volatile=True)
# Setup logger and output folders
model_name = os.path.splitext(os.path.basename(opts.config))[0]
train_writer = tensorboardX.SummaryWriter(os.path.join(opts.output_path + "/logs", model_name))
output_directory = os.path.join(opts.output_path + "/outputs", model_name)
checkpoint_directory, image_directory = prepare_sub_folder(output_directory)
shutil.copy(opts.config, os.path.join(output_directory, 'config.yaml')) # copy config file to output folder
# Start training
iterations = trainer.resume(checkpoint_directory, hyperparameters=config) if opts.resume else 0
while True:
########################## Load model #################################################
trainer = MUNIT_Trainer(config)
state_dict = torch.load(opts.checkpoint)
trainer.gen_a.load_state_dict(state_dict['a'])
trainer.gen_b.load_state_dict(state_dict['b'])
trainer.cuda()
trainer.eval()
encode_a = trainer.gen_a.encode # encoder A function
decode_a = trainer.gen_a.decode # decoder A function
encode_b = trainer.gen_b.encode # encoder B function
decode_b = trainer.gen_b.decode # decoder B function
########################## Load data #################################################
_, _, test_loader_a, test_loader_b = get_all_data_loaders(config)
if not os.path.exists(output_dir + '/' + 'output_images'):
os.makedirs(output_dir + '/' + 'output_images')
############### Extract the tensors and vectors ######################################
# Note that the batch size is set as 300.
with torch.no_grad():
for images in test_loader_a:
if images.size(0) != batch_size:
continue
images = images.cuda().detach()
# Start testing
test_images_a = images.cpu().numpy()
c_a, s_a = encode_a(images)
c_a_np = c_a.cpu().numpy()
def main(argv):
(opts, args) = parser.parse_args(argv)
cudnn.benchmark = True
# Load experiment setting
config = get_config(opts.config)
max_iter = config['max_iter']
# Setup logger and output folders
output_subfolders = prepare_logging_folders(config['output_root'],
config['experiment_name'])
logger = create_logger(
os.path.join(output_subfolders['logs'], 'train_log.log'))
shutil.copy(opts.config,
os.path.join(
output_subfolders['logs'],
'config.yaml')) # copy config file to output folder
tb_logger = tensorboard_logger.Logger(output_subfolders['logs'])
logger.info('============ Initialized logger ============')
logger.info('Config File: {}'.format(opts.config))
# Setup model and data loader
trainer = MUNIT_Trainer(config, opts)
trainer.cuda()
loaders = get_all_data_loaders(config)
val_display_images = next(iter(loaders['val']))
logger.info('Test images: {}'.format(val_display_images['A_paths']))
# Start training
iterations = trainer.resume(opts.model_path,
hyperparameters=config) if opts.resume else 0
while True:
for it, images in enumerate(loaders['train']):
trainer.update_learning_rate()
images_a = images['A']
images_b = images['B']
images_a, images_b = Variable(images_a.cuda()), Variable(
images_b.cuda())
# Main training code
trainer.dis_update(images_a, images_b, config)
trainer.gen_update(images_a, images_b, config)
# Dump training stats in log file
if (iterations + 1) % config['log_iter'] == 0:
for tag, value in trainer.loss.items():
tb_logger.scalar_summary(tag, value, iterations)
val_output_imgs = trainer.sample(
Variable(val_display_images['A'].cuda()),
Variable(val_display_images['B'].cuda()))
tb_imgs = []
for imgs in val_output_imgs.values():
tb_imgs.append(torch.cat(torch.unbind(imgs, 0), dim=2))
tb_logger.image_summary(list(val_output_imgs.keys()), tb_imgs,
iterations)
if (iterations + 1) % config['print_iter'] == 0:
logger.info(
"Iteration: {:08}/{:08} Discriminator Loss: {:.4f} Generator Loss: {:.4f}"
.format(iterations + 1, max_iter, trainer.loss['D/total'],
trainer.loss['G/total']))
# Write images
# if (iterations + 1) % config['image_save_iter'] == 0:
# val_output_imgs = trainer.sample(
# Variable(val_display_images['A'].cuda()),
# Variable(val_display_images['B'].cuda()))
#
# for key, imgs in val_output_imgs.items():
# key = key.replace('/', '_')
# write_images(imgs, config['display_size'], '{}/{}_{:08}.jpg'.format(output_subfolders['images'], key, iterations+1))
#
# logger.info('Saved images to: {}'.format(output_subfolders['images']))
# Save network weights
if (iterations + 1) % config['snapshot_save_iter'] == 0:
trainer.save(output_subfolders['models'], iterations)
iterations += 1
if iterations >= max_iter:
return
