def get_dataset(dataset_name,
root,
source,
target,
train_source_transform,
val_transform,
train_target_transform=None):
if train_target_transform is None:
train_target_transform = train_source_transform
# load datasets from common.vision.datasets
dataset = datasets.__dict__[dataset_name]
partial_dataset = partial(dataset)
train_source_dataset = dataset(root=root,
task=source,
download=True,
transform=train_source_transform)
train_target_dataset = partial_dataset(root=root,
task=target,
download=True,
transform=train_target_transform)
val_dataset = partial_dataset(root=root,
task=target,
download=True,
transform=val_transform)
if dataset_name == 'DomainNet':
test_dataset = partial_dataset(root=root,
task=target,
split='test',
download=True,
transform=val_transform)
else:
test_dataset = val_dataset
class_names = train_source_dataset.classes
num_classes = len(class_names)
return train_source_dataset, train_target_dataset, val_dataset, test_dataset, num_classes, class_names
def main(args: argparse.Namespace):
logger = CompleteLogger(args.log, args.phase)
print(args)
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
cudnn.benchmark = True
# Data loading code
normalize = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if args.center_crop:
train_transform = T.Compose([
ResizeImage(256),
T.CenterCrop(224),
T.RandomHorizontalFlip(),
T.ToTensor(), normalize
])
else:
train_transform = T.Compose([
ResizeImage(256),
T.RandomResizedCrop(224),
T.RandomHorizontalFlip(),
T.ToTensor(), normalize
])
val_transform = T.Compose(
[ResizeImage(256),
T.CenterCrop(224),
T.ToTensor(), normalize])
dataset = datasets.__dict__[args.data]
partial_dataset = partial(dataset)
train_source_dataset = dataset(root=args.root,
task=args.source,
download=True,
transform=train_transform)
train_source_loader = DataLoader(train_source_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
train_target_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=train_transform)
train_target_loader = DataLoader(train_target_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
val_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=val_transform)
val_loader = DataLoader(val_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
if args.data == 'DomainNet':
test_dataset = partial_dataset(root=args.root,
task=args.target,
split='test',
download=True,
transform=val_transform)
test_loader = DataLoader(test_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
else:
test_loader = val_loader
train_source_iter = ForeverDataIterator(train_source_loader)
train_target_iter = ForeverDataIterator(train_target_loader)
# create model
print("=> using pre-trained model '{}'".format(args.arch))
num_classes = train_source_dataset.num_classes
backbone = models.__dict__[args.arch](pretrained=True)
if args.data == 'ImageNetCaltech':
classifier = Classifier(backbone,
num_classes,
head=backbone.copy_head()).to(device)
else:
classifier = ImageClassifier(backbone, num_classes,
args.bottleneck_dim).to(device)
# define domain classifier D, D_0
D = DomainDiscriminator(in_feature=classifier.features_dim,
hidden_size=1024,
batch_norm=False).to(device)
D_0 = DomainDiscriminator(in_feature=classifier.features_dim,
hidden_size=1024,
batch_norm=False).to(device)
# define optimizer and lr scheduler
optimizer = SGD(classifier.get_parameters() + D.get_parameters() +
D_0.get_parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay,
nesterov=True)
lr_scheduler = LambdaLR(
optimizer, lambda x: args.lr *
(1. + args.lr_gamma * float(x))**(-args.lr_decay))
# define loss function
domain_adv_D = DomainAdversarialLoss(D).to(device)
domain_adv_D_0 = DomainAdversarialLoss(D_0).to(device)
# define importance weight module
importance_weight_module = ImportanceWeightModule(
D, train_target_dataset.partial_classes_idx)
# resume from the best checkpoint
if args.phase != 'train':
checkpoint = torch.load(logger.get_checkpoint_path('best'),
map_location='cpu')
classifier.load_state_dict(checkpoint)
# analysis the model
if args.phase == 'analysis':
# extract features from both domains
feature_extractor = nn.Sequential(classifier.backbone,
classifier.bottleneck).to(device)
source_feature = collect_feature(train_source_loader,
feature_extractor, device)
target_feature = collect_feature(train_target_loader,
feature_extractor, device)
# plot t-SNE
tSNE_filename = osp.join(logger.visualize_directory, 'TSNE.png')
tsne.visualize(source_feature, target_feature, tSNE_filename)
print("Saving t-SNE to", tSNE_filename)
# calculate A-distance, which is a measure for distribution discrepancy
A_distance = a_distance.calculate(source_feature, target_feature,
device)
print("A-distance =", A_distance)
return
if args.phase == 'test':
acc1 = validate(test_loader, classifier, args)
print(acc1)
return
# start training
best_acc1 = 0.
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, classifier, domain_adv_D,
domain_adv_D_0, importance_weight_module, optimizer,
lr_scheduler, epoch, args)
# evaluate on validation set
acc1 = validate(val_loader, classifier, args)
# remember best acc@1 and save checkpoint
torch.save(classifier.state_dict(),
logger.get_checkpoint_path('latest'))
if acc1 > best_acc1:
shutil.copy(logger.get_checkpoint_path('latest'),
logger.get_checkpoint_path('best'))
best_acc1 = max(acc1, best_acc1)
print("best_acc1 = {:3.1f}".format(best_acc1))
# evaluate on test set
classifier.load_state_dict(torch.load(logger.get_checkpoint_path('best')))
acc1 = validate(test_loader, classifier, args)
print("test_acc1 = {:3.1f}".format(acc1))
logger.close()
def main(args: argparse.Namespace):
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
cudnn.benchmark = True
# Data loading code
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if args.center_crop:
train_transform = transforms.Compose([
ResizeImage(256),
transforms.CenterCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), normalize
])
else:
train_transform = transforms.Compose([
ResizeImage(256),
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), normalize
])
val_transform = transforms.Compose([
ResizeImage(256),
transforms.CenterCrop(224),
transforms.ToTensor(), normalize
])
dataset = datasets.__dict__[args.data]
partial_dataset = partial(dataset)
train_source_dataset = dataset(root=args.root,
task=args.source,
download=True,
transform=train_transform)
train_source_loader = DataLoader(train_source_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
train_target_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=train_transform)
train_target_loader = DataLoader(train_target_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
val_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=val_transform)
val_loader = DataLoader(val_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
if args.data == 'DomainNet':
test_dataset = partial_dataset(root=args.root,
task=args.target,
split='test',
download=True,
transform=val_transform)
test_loader = DataLoader(test_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
else:
test_loader = val_loader
train_source_iter = ForeverDataIterator(train_source_loader)
train_target_iter = ForeverDataIterator(train_target_loader)
# create model
print("=> using pre-trained model '{}'".format(args.arch))
backbone = models.__dict__[args.arch](pretrained=True).to(device)
num_classes = train_source_dataset.num_classes
classifier = ImageClassifier(backbone,
num_classes,
bottleneck_dim=args.bottleneck_dim,
width=args.bottleneck_dim).to(device)
mdd = MarginDisparityDiscrepancy(args.margin).to(device)
class_weight_module = AutomaticUpdateClassWeightModule(
args.class_weight_update_steps, train_target_loader, classifier,
num_classes, device, args.temperature,
train_target_dataset.partial_classes_idx)
# define optimizer and lr_scheduler
# The learning rate of the classifiers are set 10 times to that of the feature extractor by default.
optimizer = SGD(classifier.get_parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.wd,
nesterov=True)
lr_scheduler = LambdaLR(
optimizer, lambda x: args.lr *
(1. + args.lr_gamma * float(x))**(-args.lr_decay))
# start training
best_acc1 = 0.
best_model = classifier.state_dict()
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, classifier, mdd,
class_weight_module, optimizer, lr_scheduler, epoch, args)
# evaluate on validation set
acc1 = validate(val_loader, classifier, args)
# remember best acc@1 and save checkpoint
if acc1 > best_acc1:
best_model = copy.deepcopy(classifier.state_dict())
best_acc1 = max(acc1, best_acc1)
print("best_acc1 = {:3.1f}".format(best_acc1))
# evaluate on test set
classifier.load_state_dict(best_model)
acc1 = validate(test_loader, classifier, args)
print("test_acc1 = {:3.1f}".format(acc1))
def main(args: argparse.Namespace):
logger = CompleteLogger(args.log, args.phase)
print(args)
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
cudnn.benchmark = True
# Data loading code
normalize = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if args.center_crop:
train_transform = T.Compose([
ResizeImage(256),
T.CenterCrop(224),
T.RandomHorizontalFlip(),
T.ToTensor(), normalize
])
else:
train_transform = T.Compose([
ResizeImage(256),
T.RandomCrop(224),
T.RandomHorizontalFlip(),
T.ToTensor(), normalize
])
val_transform = T.Compose(
[ResizeImage(256),
T.CenterCrop(224),
T.ToTensor(), normalize])
dataset = datasets.__dict__[args.data]
partial_dataset = partial(dataset)
train_source_dataset = dataset(root=args.root,
task=args.source,
download=True,
transform=train_transform)
train_source_loader = DataLoader(train_source_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
train_target_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=train_transform)
train_target_loader = DataLoader(train_target_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
drop_last=True)
val_dataset = partial_dataset(root=args.root,
task=args.target,
download=True,
transform=val_transform)
val_loader = DataLoader(val_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
if args.data == 'DomainNet':
test_dataset = partial_dataset(root=args.root,
task=args.target,
split='test',
download=True,
transform=val_transform)
test_loader = DataLoader(test_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
else:
test_loader = val_loader
train_source_iter = ForeverDataIterator(train_source_loader)
train_target_iter = ForeverDataIterator(train_target_loader)
# create model
print("=> using pre-trained model '{}'".format(args.arch))
backbone = models.__dict__[args.arch](pretrained=True)
classifier = ImageClassifier(backbone,
train_source_dataset.num_classes,
args.num_blocks,
bottleneck_dim=args.bottleneck_dim,
dropout_p=args.dropout_p).to(device)
adaptive_feature_norm = AdaptiveFeatureNorm(args.delta).to(device)
# define optimizer
# the learning rate is fixed according to origin paper
optimizer = SGD(classifier.get_parameters(),
args.lr,
weight_decay=args.weight_decay)
# resume from the best checkpoint
if args.phase != 'train':
checkpoint = torch.load(logger.get_checkpoint_path('best'),
map_location='cpu')
classifier.load_state_dict(checkpoint)
# analysis the model
if args.phase == 'analysis':
# extract features from both domains
feature_extractor = nn.Sequential(classifier.backbone,
classifier.bottleneck).to(device)
source_feature = collect_feature(train_source_loader,
feature_extractor, device)
target_feature = collect_feature(train_target_loader,
feature_extractor, device)
# plot t-SNE
tSNE_filename = osp.join(logger.visualize_directory, 'TSNE.png')
tsne.visualize(source_feature, target_feature, tSNE_filename)
print("Saving t-SNE to", tSNE_filename)
# calculate A-distance, which is a measure for distribution discrepancy
A_distance = a_distance.calculate(source_feature, target_feature,
device)
print("A-distance =", A_distance)
return
if args.phase == 'test':
acc1 = validate(test_loader, classifier, args)
print(acc1)
return
# start training
best_acc1 = 0.
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, classifier,
adaptive_feature_norm, optimizer, epoch, args)
# evaluate on validation set
acc1 = validate(val_loader, classifier, args)
# remember best acc@1 and save checkpoint
torch.save(classifier.state_dict(),
logger.get_checkpoint_path('latest'))
if acc1 > best_acc1:
shutil.copy(logger.get_checkpoint_path('latest'),
logger.get_checkpoint_path('best'))
best_acc1 = max(acc1, best_acc1)
print("best_acc1 = {:3.1f}".format(best_acc1))
# evaluate on test set
classifier.load_state_dict(torch.load(logger.get_checkpoint_path('best')))
acc1 = validate(test_loader, classifier, args)
print("test_acc1 = {:3.1f}".format(acc1))
logger.close()