def train(train_source_iter: ForeverDataIterator, train_target_iter: ForeverDataIterator, model: ImageClassifier,
mkmmd_loss: MultipleKernelMaximumMeanDiscrepancy, optimizer: SGD,
lr_scheduler: LambdaLR, epoch: int, args: argparse.Namespace):
batch_time = AverageMeter('Time', ':4.2f')
data_time = AverageMeter('Data', ':3.1f')
losses = AverageMeter('Loss', ':3.2f')
trans_losses = AverageMeter('Trans Loss', ':5.4f')
cls_accs = AverageMeter('Cls Acc', ':3.1f')
tgt_accs = AverageMeter('Tgt Acc', ':3.1f')
progress = ProgressMeter(
args.iters_per_epoch,
[batch_time, data_time, losses, trans_losses, cls_accs, tgt_accs],
prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
mkmmd_loss.train()
end = time.time()
for i in range(args.iters_per_epoch):
x_s, labels_s = next(train_source_iter)
x_t, labels_t = next(train_target_iter)
x_s = x_s.to(device)
x_t = x_t.to(device)
labels_s = labels_s.to(device)
labels_t = labels_t.to(device)
# measure data loading time
data_time.update(time.time() - end)
# compute output
y_s, f_s = model(x_s)
y_t, f_t = model(x_t)
cls_loss = F.cross_entropy(y_s, labels_s)
transfer_loss = mkmmd_loss(f_s, f_t)
loss = cls_loss + transfer_loss * args.trade_off
cls_acc = accuracy(y_s, labels_s)[0]
tgt_acc = accuracy(y_t, labels_t)[0]
losses.update(loss.item(), x_s.size(0))
cls_accs.update(cls_acc.item(), x_s.size(0))
tgt_accs.update(tgt_acc.item(), x_t.size(0))
trans_losses.update(transfer_loss.item(), x_s.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
lr_scheduler.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
progress.display(i)
def validate(val_loader: DataLoader, model: ImageClassifier, args: argparse.Namespace) -> float:
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(
len(val_loader),
[batch_time, losses, top1, top5],
prefix='Test: ')
# switch to evaluate mode
model.eval()
if args.per_class_eval:
classes = val_loader.dataset.classes
confmat = ConfusionMatrix(len(classes))
else:
confmat = None
with torch.no_grad():
end = time.time()
for i, (images, target) in enumerate(val_loader):
images = images.to(device)
target = target.to(device)
# compute output
output, _ = model(images)
loss = F.cross_entropy(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
if confmat:
confmat.update(target, output.argmax(1))
losses.update(loss.item(), images.size(0))
top1.update(acc1.item(), images.size(0))
top5.update(acc5.item(), images.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
progress.display(i)
print(' * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'
.format(top1=top1, top5=top5))
if confmat:
print(confmat.format(classes))
return top1.avg
def main(args: argparse.Namespace):
logger = CompleteLogger(args.log, args.phase)
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]
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,
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)
num_classes = train_source_dataset.num_classes
classifier = ImageClassifier(backbone,
num_classes,
bottleneck_dim=args.bottleneck_dim).to(device)
# define optimizer and lr scheduler
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))
# define loss function
mkmmd_loss = MultipleKernelMaximumMeanDiscrepancy(
kernels=[GaussianKernel(alpha=2**k) for k in range(-3, 2)],
linear=not args.non_linear)
# 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, mkmmd_loss,
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])
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 optimizer and lr scheduler
optimizer = SGD(classifier.get_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)
# define loss function
mkmmd_loss = MultipleKernelMaximumMeanDiscrepancy(
kernels=[GaussianKernel(alpha=2**k) for k in range(-3, 2)],
linear=not args.non_linear,
quadratic_program=args.quadratic_program)
# start training
best_acc1 = 0.
for epoch in range(args.epochs):
# train for one epoch
train(train_source_iter, train_target_iter, classifier, mkmmd_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))