def __init__(self, checkpoint_path, cp_name, loader, cuda):
self.cp_task = os.path.join(checkpoint_path, 'task'+cp_name+'.pt') if cp_name else os.path.join(checkpoint_path, 'task_checkpoint_{}ep.pt')
self.cp_domain = os.path.join(checkpoint_path, 'Domain_{}'+cp_name+'.pt') if cp_name else os.path.join(checkpoint_path, 'Domain_{}.pt')
self.dataloader = loader
self.cuda = cuda
self.feature_extractor = models.AlexNet(num_classes = 7, baseline = False)
self.task_classifier = models.task_classifier()
hdf_path3=test_source_3,
transform=img_transform_test)
test_source_loader = torch.utils.data.DataLoader(
dataset=test_source_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers)
target_dataset = Loader_validation(hdf_path=target_path,
transform=img_transform_test)
target_loader = torch.utils.data.DataLoader(dataset=target_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers)
task_classifier = models.task_classifier()
domain_discriminator_list = []
for i in range(3):
if args.rp_size == 4096:
disc = models.domain_discriminator_ablation_RP(
optim.SGD, args.lr_domain, args.momentum_domain,
args.l2).train()
else:
disc = models.domain_discriminator(args.rp_size, optim.SGD,
args.lr_domain,
args.momentum_domain,
args.l2).train()
domain_discriminator_list.append(disc)
#feature_extractor = models.AlexNet(num_classes = 7, baseline = False)
feature_extractor = models.get_pretrained_model(args.train_model)