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])
train_transform = transforms.Compose([
ResizeImage(256),
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), normalize
])
val_tranform = transforms.Compose([
ResizeImage(256),
transforms.CenterCrop(224),
transforms.ToTensor(), normalize
])
dataset = datasets.__dict__[args.data]
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 = 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 = dataset(root=args.root,
task=args.target,
download=True,
transform=val_tranform)
val_loader = DataLoader(val_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers)
if args.data == 'DomainNet':
test_dataset = dataset(root=args.root,
task=args.target,
evaluate=True,
download=True,
transform=val_tranform)
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).to(device)
domain_discri = DomainDiscriminator(in_feature=classifier.features_dim,
hidden_size=1024).to(device)
# define optimizer and lr scheduler
optimizer = SGD(classifier.get_parameters() +
domain_discri.get_parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay,
nesterov=True)
lr_scheduler = StepwiseLR(optimizer,
init_lr=args.lr,
gamma=0.001,
decay_rate=0.75)
# define loss function
domain_adv = DomainAdversarialLoss(domain_discri).to(device)
# 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,
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):
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]
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 = 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 = 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 = dataset(root=args.root,
task=args.target,
evaluate=True,
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))
G = models.__dict__[args.arch](pretrained=True).to(
device) # feature extractor
num_classes = train_source_dataset.num_classes
# two image classifier heads
F1 = ImageClassifierHead(G.out_features, num_classes,
args.bottleneck_dim).to(device)
F2 = ImageClassifierHead(G.out_features, num_classes,
args.bottleneck_dim).to(device)
# define optimizer
# the learning rate is fixed according to origin paper
optimizer_g = SGD(G.parameters(), lr=args.lr, weight_decay=0.0005)
optimizer_f = SGD(F1.get_parameters() + F2.get_parameters(),
momentum=0.9,
lr=args.lr,
weight_decay=0.0005)
# start training
best_acc1 = 0.
best_results = None
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, G, F1, F2, optimizer_g,
optimizer_f, epoch, args)
# evaluate on validation set
results = validate(val_loader, G, F1, F2, args)
# remember best acc@1 and save checkpoint
if max(results) > best_acc1:
best_G, best_F1, best_F2 = copy.deepcopy(
G.state_dict()), copy.deepcopy(F1.state_dict()), copy.deepcopy(
F2.state_dict())
best_acc1 = max(results)
best_results = results
print("best_acc1 = {:3.1f}, results = {}".format(best_acc1, best_results))
# evaluate on test set
G.load_state_dict(best_G)
F1.load_state_dict(best_F1)
F2.load_state_dict(best_F2)
results = validate(test_loader, G, F1, F2, args)
print("test_acc1 = {:3.1f}".format(max(results)))
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])
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]
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 = 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 = 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 = dataset(root=args.root,
task=args.target,
evaluate=True,
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)
num_classes = train_source_dataset.num_classes
classifier = ImageClassifier(backbone, num_classes).to(device)
# define loss function
if args.adversarial:
thetas = [
Theta(dim).to(device)
for dim in (classifier.features_dim, num_classes)
]
else:
thetas = None
jmmd_loss = JointMultipleKernelMaximumMeanDiscrepancy(
kernels=([GaussianKernel(alpha=2**k) for k in range(-3, 2)],
(GaussianKernel(sigma=0.92, track_running_stats=False), )),
linear=args.linear,
thetas=thetas).to(device)
parameters = classifier.get_parameters()
if thetas is not None:
parameters += [{
"params": theta.parameters(),
'lr_mult': 0.1
} for theta in thetas]
# define optimizer
optimizer = SGD(parameters,
args.lr,
momentum=args.momentum,
weight_decay=args.wd,
nesterov=True)
lr_sheduler = StepwiseLR(optimizer,
init_lr=args.lr,
gamma=0.0003,
decay_rate=0.75)
# start training
best_acc1 = 0.
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, classifier, jmmd_loss,
optimizer, lr_sheduler, 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):
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])
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]
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 = 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 = 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)
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).to(device)
domain_discri = DomainDiscriminator(in_feature=classifier.features_dim, hidden_size=1024).to(device)
# define optimizer and lr scheduler
optimizer = SGD(classifier.get_parameters() + domain_discri.get_parameters(),
args.lr, momentum=args.momentum, weight_decay=args.weight_decay, nesterov=True)
lr_scheduler = StepwiseLR(optimizer, init_lr=args.lr, gamma=0.001, decay_rate=0.75)
# define loss function
domain_adv = DomainAdversarialLoss(domain_discri).to(device)
# 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, domain_adv, 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 = classifier.state_dict()
torch.save(best_model, 'best_model.pth.tar')
best_acc1 = max(acc1, best_acc1)
print("best_acc1 = {:3.1f}".format(best_acc1))
# visualize the results using T-SNE
classifier.load_state_dict(best_model)
classifier.eval()
features, labels, domains = [], [], []
source_val_dataset = dataset(root=args.root, task=args.source, download=True, transform=val_transform)
source_val_loader = DataLoader(source_val_dataset, batch_size=args.batch_size, shuffle=False, num_workers=args.workers)
with torch.no_grad():
for loader in [source_val_loader, val_loader]:
for i, (images, target) in enumerate(loader):
images = images.to(device)
target = target.to(device)
# compute output
_, f = classifier(images)
features.extend(f.cpu().numpy().tolist())
labels.extend(target)
domains = np.concatenate((np.ones(len(source_val_dataset)), np.zeros(len(val_dataset))))
features, labels = np.array(features), np.array(labels)
print("source:", len(source_val_dataset), "target:", len(val_dataset))
X_tsne = TSNE(n_components=2, random_state=33).fit_transform(features)
plt.figure(figsize=(10, 10))
plt.scatter(X_tsne[:, 0], X_tsne[:, 1], c=domains, cmap=col.ListedColormap(["r", "b"]), s=2)
plt.savefig(os.path.join('{}_{}2{}.pdf'.format("dann", args.source, args.target)))