def train():
    best_test_acc = 0.
    class_acc_best = 0.
    for epoch in range(args.epochs):
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

        train_overall_acc, train_class_acc, train_obj = train_step(train_queue, model, criterion, optimizer, args)
        test_overall_acc, test_class_acc, test_obj = infer(test_queue, model, criterion)
        if test_overall_acc > best_test_acc:
            best_test_acc = test_overall_acc
            class_acc_best = test_class_acc
            utils.save(model, os.path.join(args.save, 'best_weights.pt'))

        logging.info(
            'train_overall_acc %f\t train_class_acc %f\t test_overall_acc %f\t test_class_acc %f\t best_test_overall_acc %f\t test_class_acc_when_best %f',
            train_overall_acc, train_class_acc, test_overall_acc, test_class_acc, best_test_acc, class_acc_best)
        utils.save(model, os.path.join(args.save, 'weights.pt'))
        scheduler.step()

    logging.info(
        'Finish! best_test_overall_acc %f\t test_class_acc_when_best %f', best_test_acc, class_acc_best) 

def train():
    best_val_acc = 0.
    best_test_acc = 0.
    for epoch in range(args.epochs):
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

        train_acc, train_obj = train_step(train_queue, model, criterion, optimizer)
        valid_acc, valid_obj = infer(valid_queue, model, criterion)
        test_acc, test_obj = infer(test_queue, model, criterion)
        if valid_acc > best_val_acc:
            best_val_acc = valid_acc
            test_acc_when_best_val = test_acc
            utils.save(model, os.path.join(args.save, 'best_weights.pt'))
        if test_acc > best_test_acc:
            best_test_acc = test_acc
        logging.info('train_acc %f\tvalid_acc %f\tbest_val_acc %f\ttest_acc %f\tbest_test_acc %f\tfinal_best_test %f',
                     train_acc, valid_acc, best_val_acc, test_acc, best_test_acc, test_acc_when_best_val)

        utils.save(model, os.path.join(args.save, 'weights.pt'))
        scheduler.step()
    logging.info(
        'Finish! best_val_acc %f\t test_class_acc_when_best %f \t best test %f',
        best_test_acc, test_acc_when_best_val, best_test_acc) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = True
    
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc_top1 %f', valid_acc_top1)
        logging.info('valid_acc_top5 %f', valid_acc_top5)

        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = False
    cudnn.deterministic = True
    
    args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    build_fn = get_builder(args.dataset)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc %f', valid_acc_top1)
        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = True
    
    args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    build_fn = get_builder(args.dataset)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc %f', valid_acc_top1)
        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = True
    
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc_top1 %f', valid_acc_top1)
        logging.info('valid_acc_top5 %f', valid_acc_top5)

        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = False
    cudnn.deterministic = True
    
    args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    build_fn = get_builder(args.dataset)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc %f', valid_acc_top1)
        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = False
    cudnn.deterministic = True
    
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc_top1 %f', valid_acc_top1)
        logging.info('valid_acc_top5 %f', valid_acc_top5)

        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    torch.cuda.manual_seed_all(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = False
    cudnn.deterministic = True
    
    args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    build_fn = get_builder(args.dataset)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc %f', valid_acc_top1)
        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    cudnn.enabled = True
    cudnn.benchmark = False
    cudnn.deterministic = True
    torch.cuda.manual_seed(args.seed)
    
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc_top1 %f', valid_acc_top1)
        logging.info('valid_acc_top5 %f', valid_acc_top5)

        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('No GPU found!')
        sys.exit(1)
    
    np.random.seed(args.seed)
    cudnn.benchmark = False
    torch.manual_seed(args.seed)
    cudnn.enabled = True
    torch.cuda.manual_seed(args.seed)
    
    args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
    logging.info("Args = %s", args)
    
    _, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
    build_fn = get_builder(args.dataset)
    train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)

    while epoch < args.epochs:
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
        logging.info('train_acc %f', train_acc)
        valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
        logging.info('valid_acc %f', valid_acc_top1)
        epoch += 1
        is_best = False
        if valid_acc_top1 > best_acc_top1:
            best_acc_top1 = valid_acc_top1
            is_best = True
        utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 

def main():
    if not torch.cuda.is_available():
        logging.info('no gpu device available')
        sys.exit(1)

    np.random.seed(args.seed)
    torch.cuda.set_device(args.gpu)
    cudnn.benchmark = True
    torch.manual_seed(args.seed)
    cudnn.enabled = True
    torch.cuda.manual_seed(args.seed)
    logging.info('gpu device = %d' % args.gpu)
    logging.info("args = %s", args)

    genotype = eval("genotypes.%s" % args.arch)
    model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
    model = model.cuda()

    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

    criterion = nn.CrossEntropyLoss()
    criterion = criterion.cuda()
    optimizer = torch.optim.SGD(
        model.parameters(),
        args.learning_rate,
        momentum=args.momentum,
        weight_decay=args.weight_decay
    )

    train_transform, valid_transform = utils._data_transforms_cifar10(args)
    train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
    valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)

    train_queue = torch.utils.data.DataLoader(
        train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)

    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)

    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))

    for epoch in range(args.epochs):
        scheduler.step()
        logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
        model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

        train_acc, train_obj = train(train_queue, model, criterion, optimizer)
        logging.info('train_acc %f', train_acc)

        valid_acc, valid_obj = infer(valid_queue, model, criterion)
        logging.info('valid_acc %f', valid_acc)

        utils.save(model, os.path.join(args.save, 'weights.pt')) 

def main():
  if not torch.cuda.is_available():
    logging.info('no gpu device available')
    sys.exit(1)

  np.random.seed(args.seed)
  torch.cuda.set_device(args.gpu)
  cudnn.benchmark = True
  torch.manual_seed(args.seed)
  cudnn.enabled=True
  torch.cuda.manual_seed(args.seed)
  logging.info('gpu device = %d' % args.gpu)
  logging.info("args = %s", args)

  genotype = eval("genotypes.%s" % args.arch)
  model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
  model = model.cuda()

  logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()
  optimizer = torch.optim.SGD(
    model.parameters(),
    args.learning_rate,
    momentum=args.momentum,
    weight_decay=args.weight_decay
  )

  train_transform, valid_transform = utils._data_transforms_cifar10(args)
  train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
  valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)

  train_queue = torch.utils.data.DataLoader(
    train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)

  valid_queue = torch.utils.data.DataLoader(
    valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)

  scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))

  for epoch in range(args.epochs):
    scheduler.step()
    logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
    model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

    train_acc, train_obj = train(train_queue, model, criterion, optimizer)
    logging.info('train_acc %f', train_acc)

    valid_acc, valid_obj = infer(valid_queue, model, criterion)
    logging.info('valid_acc %f', valid_acc)

    utils.save(model, os.path.join(args.save, 'weights.pt')) 

def main():
  if not torch.cuda.is_available():
    logging.info('no gpu device available')
    sys.exit(1)

  np.random.seed(args.seed)
  torch.cuda.set_device(args.gpu)
  cudnn.benchmark = True
  torch.manual_seed(args.seed)
  cudnn.enabled=True
  torch.cuda.manual_seed(args.seed)
  logging.info('gpu device = %d' % args.gpu)
  logging.info("args = %s", args)

  genotype = eval("genotypes.%s" % args.arch)
  model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
  model = model.cuda()

  logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()
  optimizer = torch.optim.SGD(
      model.parameters(),
      args.learning_rate,
      momentum=args.momentum,
      weight_decay=args.weight_decay
      )

  train_transform, valid_transform = utils._data_transforms_cifar10(args)
  train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
  valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)

  train_queue = torch.utils.data.DataLoader(
      train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)

  valid_queue = torch.utils.data.DataLoader(
      valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)

  scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))

  for epoch in range(args.epochs):
    scheduler.step()
    logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
    model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

    train_acc, train_obj = train(train_queue, model, criterion, optimizer)
    logging.info('train_acc %f', train_acc)

    valid_acc, valid_obj = infer(valid_queue, model, criterion)
    logging.info('valid_acc %f', valid_acc)

    utils.save(model, os.path.join(args.save, 'weights.pt')) 

def main():
    if not torch.cuda.is_available():
        logging.info('no gpu device available')
        sys.exit(1)

    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.cuda.set_device(args.gpu)
    torch.backends.cudnn.benchmark = True
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    logging.info('gpu device = %d' % args.gpu)
    logging.info("args = %s", args)

    model = CNN(args)
    model.cuda()

    controller = Controller(args)
    controller.cuda()
    baseline = None

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.child_lr_max,
        momentum=args.momentum,
        weight_decay=args.weight_decay,
    )

    controller_optimizer = torch.optim.Adam(
        controller.parameters(),
        args.controller_lr,
        betas=(0.1,0.999),
        eps=1e-3,
    )

    train_loader, reward_loader, valid_loader = get_loaders(args)

    scheduler = utils.LRScheduler(optimizer, args)

    for epoch in range(args.epochs):
        lr = scheduler.update(epoch)
        logging.info('epoch %d lr %e', epoch, lr)

        # training
        train_acc = train(train_loader, model, controller, optimizer)
        logging.info('train_acc %f', train_acc)

        train_controller(reward_loader, model, controller, controller_optimizer)

        # validation
        valid_acc = infer(valid_loader, model, controller)
        logging.info('valid_acc %f', valid_acc)

        utils.save(model, os.path.join(args.save, 'weights.pt')) 

def main():
    if not torch.cuda.is_available():
        logging.info('no gpu device available')
        sys.exit(1)

    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.cuda.set_device(args.gpu)
    torch.backends.cudnn.benchmark = True
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)
    logging.info('gpu device = %d' % args.gpu)
    logging.info("args = %s", args)

    model = CNN(args)
    model.cuda()

    controller = Controller(args)
    controller.cuda()
    baseline = None

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.child_lr_max,
        momentum=args.momentum,
        weight_decay=args.weight_decay,
    )

    controller_optimizer = torch.optim.Adam(
        controller.parameters(),
        args.controller_lr,
        betas=(0.1,0.999),
        eps=1e-3,
    )

    train_loader, reward_loader, valid_loader = get_loaders(args)

    scheduler = utils.LRScheduler(optimizer, args)

    for epoch in range(args.epochs):
        lr = scheduler.update(epoch)
        logging.info('epoch %d lr %e', epoch, lr)

        # training
        train_acc = train(train_loader, model, controller, optimizer)
        logging.info('train_acc %f', train_acc)

        train_controller(reward_loader, model, controller, controller_optimizer)

        # validation
        valid_acc = infer(valid_loader, model, controller)
        logging.info('valid_acc %f', valid_acc)

        utils.save(model, os.path.join(args.save, 'weights.pt')) 

def main():
  if not torch.cuda.is_available():
    logging.info('no gpu device available')
    sys.exit(1)

  np.random.seed(args.seed)
  torch.cuda.set_device(args.gpu)
  cudnn.benchmark = True
  torch.manual_seed(args.seed)
  cudnn.enabled=True
  torch.cuda.manual_seed(args.seed)
  logging.info('gpu device = %d' % args.gpu)
  logging.info("args = %s", args)

  genotype = eval("genotypes.%s" % args.arch)
  model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
  model = model.cuda()

  logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()
  optimizer = torch.optim.SGD(
      model.parameters(),
      args.learning_rate,
      momentum=args.momentum,
      weight_decay=args.weight_decay
      )

  train_transform, valid_transform = utils._data_transforms_cifar10(args)
  train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
  valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)

  train_queue = torch.utils.data.DataLoader(
      train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)

  valid_queue = torch.utils.data.DataLoader(
      valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)

  scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))

  best_val_acc = 0.
  for epoch in range(args.epochs):
    scheduler.step()
    logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
    model.drop_path_prob = args.drop_path_prob * epoch / args.epochs

    train_acc, train_obj = train(train_queue, model, criterion, optimizer)
    logging.info('train_acc %f', train_acc)

    with torch.no_grad():
      valid_acc, valid_obj = infer(valid_queue, model, criterion)
      if valid_acc > best_val_acc:
        best_val_acc = valid_acc
        utils.save(model, os.path.join(args.save, 'best_weights.pt'))
      logging.info('valid_acc %f\tbest_val_acc %f', valid_acc, best_val_acc)

    utils.save(model, os.path.join(args.save, 'weights.pt'))