f'Experiment_Code: app_02;\n'
os.environ['CUDA_VISIBLE_DEVICES'] = '1,2,3'
device = 'cuda'
torch.backends.cudnn.benchmark = True
transform = transforms.Compose([
transforms.Resize(args.size),
transforms.CenterCrop(args.size),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
])
loader, _, _ = iPERLoader(data_root=args.path,
batch=128,
transform=transform).data_load()
model = VQVAE().to(device)
model = nn.DataParallel(model).cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
scheduler = None
if args.sched == 'cycle':
scheduler = CycleScheduler(optimizer,
args.lr,
n_iter=len(loader) * args.epoch,
momentum=None)
print('Loading Model...', end='')
model.load_state_dict(
win='board')
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
device = 'cuda'
torch.backends.cudnn.benchmark = True
transform = transforms.Compose([
transforms.Resize(args.size),
transforms.CenterCrop(args.size),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
])
# TODO use a little set for sanity check
# _, _, loader = iPERLoader(data_root=args.path, batch=args.batch_size, transform=transform).data_load()
_, loader, _ = iPERLoader(data_root=args.path,
batch=args.batch_size,
transform=transform).data_load()
# model for image
model_img = VQVAE().to(device)
model_img = nn.DataParallel(model_img).cuda()
if is_load_model_img is True:
print('Loading model_img ...', end='')
model_img.load_state_dict(torch.load(args.model_img_path))
model_img.eval()
print('Done')
else:
print('model_img Initialized.')
# optimizer_img = optim.Adam(model_img.parameters(), lr=args.lr)
# model for condition
f'Experiment_Code: {EXPERIMENT_CODE};\n',
win='board')
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
device = 'cuda'
transform = transforms.Compose([
transforms.Resize(args.size),
transforms.CenterCrop(args.size),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
])
# TODOn use a little set for sanity check
# _, _, loader = iPERLoader(data_root=args.path, batch=BATCH_SIZE, transform=transform).data_load()
loader, _, _ = iPERLoader(data_root=args.path,
batch=BATCH_SIZE,
transform=transform).data_load()
# model
model = VQVAE().to(device)
model = nn.DataParallel(model).to(device)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
scheduler = None
if args.sched == 'cycle':
scheduler = CycleScheduler(optimizer,
args.lr,
n_iter=len(loader) * args.epoch,
momentum=None)
print('Loading Model...', end='')
model.load_state_dict(