def validate(val_loader: DataLoader, model: ImageClassifier, args: argparse.Namespace):
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 get_ssl_dataloader(purpose: str, source_loader: DataLoader,
target_loader: DataLoader, model: ImageClassifier,
args: argparse.Namespace) -> DataLoader:
ssl = SSL(purpose,
target_dataloader=target_loader,
source_dataloader=source_loader,
percentile_rank=args.ssl_percentile_rank,
weight_inferred_dataset=args.ssl_weight_inferred_dataset)
# switch to evaluate mode
model.eval()
with torch.no_grad():
for i, (images, target) in enumerate(target_loader):
images = images.to(device)
# compute output
output, _ = model(images)
ssl.add_predictions(output)
inferred_dataloader = ssl.get_semi_supervised_dataloader()
return inferred_dataloader
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)))
