print_args(args)
source_root = os.path.join(args.data_root, args.source)
source_label = os.path.join(args.data_root, args.source + "_list.txt")
target_root = os.path.join(args.data_root, args.target)
target_label = os.path.join(args.data_root, args.target + "6_list.txt")
train_transform = transforms.Compose([
transforms.Scale((256, 256)),
transforms.CenterCrop((224, 224)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
source_set = VisDAImage(source_root, source_label, train_transform)
target_set = VisDAImage(target_root, target_label, train_transform)
assert len(source_set) == 152397
assert len(target_set) == 28978
source_loader = torch.utils.data.DataLoader(source_set,
batch_size=args.batch_size,
shuffle=args.shuffle,
num_workers=args.num_workers)
target_loader = torch.utils.data.DataLoader(target_set,
batch_size=args.batch_size,
shuffle=args.shuffle,
num_workers=args.num_workers)
if args.model == 'resnet101':
result = open(
os.path.join(args.result,
"Visda_IAFN_" + args.post + '.' + args.repeat + "_score.txt"),
"a")
t_root = os.path.join(args.data_root, args.target)
t_label = os.path.join(args.data_root, args.target + "6_list.txt")
data_transform = transforms.Compose([
transforms.Scale((256, 256)),
transforms.CenterCrop((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
t_set = VisDAImage(t_root, t_label, data_transform)
assert len(t_set) == 28978
t_loader = torch.utils.data.DataLoader(t_set,
batch_size=args.batch_size,
shuffle=args.shuffle,
num_workers=args.num_workers)
netG = ResBase50().cuda()
netF = ResClassifier(class_num=args.class_num).cuda()
netG.eval()
netF.eval()
for epoch in range(args.epoch / 2, args.epoch + 1):
if epoch % 10 != 0:
continue