Python torch.backends.cudnn.enabled() Examples

def initial_setup(self, args):
        ############
        logging.info(f"run pid: {os.getpid()} parent: {os.getppid()}")
        logging.info("#########")
        logging.info(args.__dict__)
        logging.info(f"Rank: {args.rank} World_size: {args.world_size}, Run {args.run_name}")

        args.cuda = torch.cuda.is_available()
        logging.info(f"Pytorch version: {torch.__version__}")
        logging.info("Using CUDA: {} CUDA AVAIL: {} #DEVICES: {} VERSION: {}".format(
            args.cuda, torch.cuda.is_available(), torch.cuda.device_count(),
            torch.version.cuda))
        if not args.cuda:
            self.device = 'cpu'
        else:
            self.device = 'cuda'
            cudnn.benchmark = True
            cudnn.enabled = True

        random.seed(args.seed) # The seed needs to be constant between processes.
        torch.manual_seed(args.seed)
        torch.cuda.manual_seed_all(args.seed) 

def main():
    # Parse the JSON arguments
    config_args = parse_args()

    # Create the experiment directories
    _, config_args.summary_dir, config_args.checkpoint_dir = create_experiment_dirs(
        config_args.experiment_dir)

    model = MobileNetV2(config_args)

    if config_args.cuda:
        model.cuda()
        cudnn.enabled = True
        cudnn.benchmark = True

    print("Loading Data...")
    data = CIFAR10Data(config_args)
    print("Data loaded successfully\n")

    trainer = Train(model, data.trainloader, data.testloader, config_args)

    if config_args.to_train:
        try:
            print("Training...")
            trainer.train()
            print("Training Finished\n")
        except KeyboardInterrupt:
            pass

    if config_args.to_test:
        print("Testing...")
        trainer.test(data.testloader)
        print("Testing Finished\n") 

def main():
  if not torch.cuda.is_available():
    logging.info('no gpu device available')
    sys.exit(1)
  cudnn.enabled=True
  logging.info("args = %s", args)

  genotype = eval("genotypes.%s" % args.arch)
  model = Network(args.init_channels, CLASSES, args.layers, args.auxiliary, genotype)
  model = nn.DataParallel(model)
  model = model.cuda()
  model.load_state_dict(torch.load(args.model_path)['state_dict'])

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  validdir = os.path.join(args.data, 'val')
  normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  valid_data = dset.ImageFolder(
    validdir,
    transforms.Compose([
      transforms.Resize(256),
      transforms.CenterCrop(224),
      transforms.ToTensor(),
      normalize,
    ]))

  valid_queue = torch.utils.data.DataLoader(
    valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=False, num_workers=4)

  model.module.drop_path_prob = 0.0
  valid_acc_top1, valid_acc_top5, valid_obj = infer(valid_queue, model, criterion)
  logging.info('Valid_acc_top1 %f', valid_acc_top1)
  logging.info('Valid_acc_top5 %f', valid_acc_top5) 

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()
  utils.load(model, args.model_path)

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  _, test_transform = utils._data_transforms_cifar10(args)
  test_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=test_transform)

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

  model.drop_path_prob = args.drop_path_prob
  with torch.no_grad():
    test_acc, test_obj = infer(test_queue, model, criterion)
  logging.info('test_acc %f', test_acc) 

def main(args):
    cudnn.benchmark = True
    cudnn.enabled = True
    
    save_path = args.logs_dir
    sys.stdout = Logger(osp.join(args.logs_dir, 'log'+ str(args.merge_percent)+ time.strftime(".%m_%d_%H:%M:%S") + '.txt'))

    # get all unlabeled data for training
    dataset_all = datasets.create(args.dataset, osp.join(args.data_dir, args.dataset))
    new_train_data, cluster_id_labels = change_to_unlabel(dataset_all)

    num_train_ids = len(np.unique(np.array(cluster_id_labels)))
    nums_to_merge = int(num_train_ids * args.merge_percent)

    BuMain = Bottom_up(model_name=args.arch, batch_size=args.batch_size, 
            num_classes=num_train_ids,
            dataset=dataset_all,
            u_data=new_train_data, save_path=args.logs_dir, max_frames=args.max_frames,
            embeding_fea_size=args.fea)


    for step in range(int(1/args.merge_percent)-1):
        print('step: ',step)

        BuMain.train(new_train_data, step, loss=args.loss) 

        BuMain.evaluate(dataset_all.query, dataset_all.gallery)

        # get new train data for the next iteration
        print('----------------------------------------bottom-up clustering------------------------------------------------')
        cluster_id_labels, new_train_data = BuMain.get_new_train_data(cluster_id_labels, nums_to_merge, size_penalty=args.size_penalty)
        print('\n\n') 

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()
    utils.load(model, args.model_path)

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

    criterion = nn.CrossEntropyLoss()
    criterion = criterion.cuda()

    _, test_transform = utils.data_transforms_cifar10(args)
    test_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=test_transform)

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

    model.drop_path_prob = args.drop_path_prob
    test_acc, test_obj = infer(test_queue, model, criterion)
    logging.info('test_acc %f', 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)
    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 _init_random_and_device(self):
        # Set random seed and cuda device
        np.random.seed(self.args.seed)
        cudnn.benchmark = True
        torch.manual_seed(self.args.seed)
        cudnn.enabled = True
        torch.cuda.manual_seed(self.args.seed)
        max_free_gpu_id, gpus_info = dutils.get_gpus_memory_info()
        self.device_id = max_free_gpu_id
        self.gpus_info = gpus_info
        self.device = torch.device('cuda:{}'.format(0 if self.args.multi_gpus else self.device_id)) 

def _init_device(self):
        if not torch.cuda.is_available():
            self.logger.info('no gpu device available')
            sys.exit(1)
        self.current_gpu, _ = dutils.get_gpus_memory_info()
        np.random.seed(self.args.seed)
        torch.cuda.set_device(self.current_gpu)
        cudnn.benchmark = True
        torch.manual_seed(self.args.seed)
        cudnn.enabled = True
        torch.cuda.manual_seed(self.args.seed)
        self.logger.info('gpu device = %d', self.current_gpu) 

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()
  utils.load(model, args.model_path)

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  _, test_transform = utils._data_transforms_cifar10(args)
  test_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=test_transform)

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

  model.drop_path_prob = args.drop_path_prob
  test_acc, test_obj = infer(test_queue, model, criterion)
  logging.info('test_acc %f', test_acc) 

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()
  utils.load(model, args.model_path)

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  _, test_transform = utils._data_transforms_cifar10(args)
  test_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=test_transform)

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

  model.drop_path_prob = args.drop_path_prob
  test_acc, test_obj = infer(test_queue, model, criterion)
  logging.info('test_acc %f', 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 = 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 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()
  utils.load(model, args.model_path)

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  _, test_transform = utils._data_transforms_cifar10(args)
  test_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=test_transform)

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

  model.drop_path_prob = args.drop_path_prob
  test_acc, test_obj = infer(test_queue, model, criterion)
  logging.info('test_acc %f', test_acc) 

def main(args):
    cudnn.benchmark = True
    cudnn.enabled = True
    
    save_path = args.logs_dir
    sys.stdout = Logger(osp.join(args.logs_dir, 'log'+ str(args.merge_percent)+ time.strftime(".%m_%d_%H:%M:%S") + '.txt'))

    # get all unlabeled data for training
    dataset_all = datasets.create(args.dataset, osp.join(args.data_dir, args.dataset))
    new_train_data, cluster_id_labels = change_to_unlabel(dataset_all)

    num_train_ids = len(np.unique(np.array(cluster_id_labels)))
    nums_to_merge = int(num_train_ids * args.merge_percent)

    BuMain = Bottom_up(model_name=args.arch, batch_size=args.batch_size, 
            num_classes=num_train_ids,
            dataset=dataset_all,
            u_data=new_train_data, save_path=args.logs_dir, max_frames=args.max_frames,
            embeding_fea_size=args.fea)


    for step in range(int(1/args.merge_percent)-1):
        print('step: ',step)

        BuMain.train(new_train_data, step, loss=args.loss) 

        
        BuMain.evaluate(dataset_all.query, dataset_all.gallery)

        # get new train data for the next iteration
        print('----------------------------------------bottom-up clustering------------------------------------------------')
        cluster_id_labels, new_train_data = BuMain.get_new_train_data_v2(cluster_id_labels, nums_to_merge, step, penalty=args.size_penalty)
        print('\n\n') 

def __init__(self, args, logger):
        self.args = args
        self.logger = logger
        self.writer = SummaryWriter(args.log_dir)
        cudnn.enabled = True

        # set up model
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.model = get_aux_net(args.network.arch)(aux_classes=args.aux_classes + 1, classes=args.n_classes)
        self.model = self.model.to(self.device)

        if args.mode == 'train':
            # set up optimizer, lr scheduler and loss functions
            optimizer = get_optimizer(self.args.training.optimizer)
            optimizer_params = {k: v for k, v in self.args.training.optimizer.items() if k != "name"}
            self.optimizer = optimizer(self.model.parameters(), **optimizer_params)
            self.scheduler = get_scheduler(self.optimizer, self.args.training.lr_scheduler)

            self.class_loss_func = nn.CrossEntropyLoss()

            self.start_iter = 0

            # resume
            if args.training.resume:
                self.load(args.model_dir + '/' + args.training.resume)

            cudnn.benchmark = True

        elif args.mode == 'val':
            self.load(os.path.join(args.model_dir, args.validation.model))
        else:
            self.load(os.path.join(args.model_dir, args.testing.model)) 

def run(args):
    cudnn.benchmark = True
    cudnn.enabled = True
    if args.mode == 'train':
        trainer = create_trainer(args)
        model = VariationalNetworkModel(args)
        trainer.fit(model)
    else:  # args.mode == 'test' or args.mode == 'challenge'
        assert args.checkpoint is not None
        model = VariationalNetworkModel.load_from_checkpoint(
            str(args.checkpoint))
        model.hparams = args
        model.hparams.sample_rate = 1.
        trainer = create_trainer(args)
        trainer.test(model) 

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
    
    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 = 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)
    
    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
    
    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 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')) 

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():

    args = parse_args()
    cfg.set_args(args.gpu_ids)
    cudnn.fastest = True
    cudnn.benchmark = True
    cudnn.deterministic = False
    cudnn.enabled = True

    tester = Tester(args.test_epoch)
    tester._make_batch_generator()
    tester._make_model()

    preds = []

    with torch.no_grad():
        for itr, input_img in enumerate(tqdm(tester.batch_generator)):
            
            # forward
            coord_out = tester.model(input_img)

            if cfg.flip_test:
                flipped_input_img = flip(input_img, dims=3)
                flipped_coord_out = tester.model(flipped_input_img)
                flipped_coord_out[:, :, 0] = cfg.output_shape[1] - flipped_coord_out[:, :, 0] - 1
                for pair in tester.flip_pairs:
                    flipped_coord_out[:, pair[0], :], flipped_coord_out[:, pair[1], :] = flipped_coord_out[:, pair[1], :].clone(), flipped_coord_out[:, pair[0], :].clone()
                coord_out = (coord_out + flipped_coord_out)/2.

            vis = False
            if vis:
                filename = str(itr)
                tmpimg = input_img[0].cpu().numpy()
                tmpimg = tmpimg * np.array(cfg.pixel_std).reshape(3,1,1) + np.array(cfg.pixel_mean).reshape(3,1,1)
                tmpimg = tmpimg.astype(np.uint8)
                tmpimg = tmpimg[::-1, :, :]
                tmpimg = np.transpose(tmpimg,(1,2,0)).copy()
                tmpkps = np.zeros((3,tester.joint_num))
                tmpkps[:2,:] = coord_out[0,:,:2].cpu().numpy().transpose(1,0) / cfg.output_shape[0] * cfg.input_shape[0]
                tmpkps[2,:] = 1
                tmpimg = vis_keypoints(tmpimg, tmpkps, tester.skeleton)
                cv2.imwrite(filename + '_output.jpg', tmpimg)

            coord_out = coord_out.cpu().numpy()
            preds.append(coord_out)
            
    # evaluate
    preds = np.concatenate(preds, axis=0)
    tester._evaluate(preds, cfg.result_dir) 

def main(args):
    cudnn.benchmark = True
    cudnn.enabled = True
    save_path = args.logs_dir
    total_step = 100//args.EF + 1
    sys.stdout = Logger(osp.join(args.logs_dir, 'log'+ str(args.EF)+ time.strftime(".%m_%d_%H:%M:%S") + '.txt'))

    # get all the labeled and unlabeled data for training
    dataset_all = datasets.create(args.dataset, osp.join(args.data_dir, args.dataset))
    num_all_examples = len(dataset_all.train)
    l_data, u_data = get_one_shot_in_cam1(dataset_all, load_path="./examples/oneshot_{}_used_in_paper.pickle".format(dataset_all.name))
    
    resume_step, ckpt_file = -1, ''
    if args.resume:
        resume_step, ckpt_file = resume(args) 

    # initial the EUG algorithm 
    eug = EUG(model_name=args.arch, batch_size=args.batch_size, mode=args.mode, num_classes=dataset_all.num_train_ids, 
            data_dir=dataset_all.images_dir, l_data=l_data, u_data=u_data, save_path=args.logs_dir, max_frames=args.max_frames)


    new_train_data = l_data 
    for step in range(total_step):
        # for resume
        if step < resume_step: 
            continue

        nums_to_select = min(int( len(u_data) * (step+1) * args.EF / 100 ),  len(u_data))
        print("This is running {} with EF={}%, step {}:\t Nums_to_be_select {}, \t Logs-dir {}".format(
                args.mode, args.EF, step,  nums_to_select, save_path))

        # train the model or load ckpt        
        eug.train(new_train_data, step, epochs=70, step_size=55, init_lr=0.1) if step != resume_step else eug.resume(ckpt_file, step)

        # pseudo-label and confidence score
        pred_y, pred_score = eug.estimate_label()

        # select data
        selected_idx = eug.select_top_data(pred_score, nums_to_select)

        # add new data
        new_train_data = eug.generate_new_train_data(selected_idx, pred_y)

        # evluate
        eug.evaluate(dataset_all.query, dataset_all.gallery) 

def main():
    best_score = 0
    args = parse()
    if not args.no_logger:
        tee.Tee(args.cache+'/log.txt')
    print(vars(args))
    print('experiment folder: {}'.format(experiment_folder()))
    print('git hash: {}'.format(get_script_dir_commit_hash()))
    seed(args.manual_seed)
    cudnn.benchmark = not args.disable_cudnn_benchmark
    cudnn.enabled = not args.disable_cudnn

    metrics = get_metrics(args.metrics)
    tasks = get_tasks(args.tasks)
    model, criterion = get_model(args)
    if args.optimizer == 'sgd':
        optimizer = torch.optim.SGD(model.parameters(), args.lr,
                                    momentum=args.momentum,
                                    weight_decay=args.weight_decay)
    elif args.optimizer == 'adam':
        optimizer = torch.optim.Adam(model.parameters(), args.lr,
                                     weight_decay=args.weight_decay)
    else:
        assert False, "invalid optimizer"

    if args.resume:
        best_score = checkpoints.load(args, model, optimizer)
    print(model)
    trainer = train.Trainer()
    train_loader, val_loader = get_dataset(args)

    if args.evaluate:
        scores = validate(trainer, val_loader, model, criterion, args, metrics, tasks, -1)
        print(scores)
        score_file(scores, "{}/model_999.txt".format(args.cache))
        return

    if args.warmups > 0:
        for i in range(args.warmups):
            print('warmup {}'.format(i))
            trainer.validate(train_loader, model, criterion, -1, metrics, args)
    for epoch in range(args.start_epoch, args.epochs):
        if args.distributed:
            trainer.train_sampler.set_epoch(epoch)
        scores = {}
        scores.update(trainer.train(train_loader, model, criterion, optimizer, epoch, metrics, args))
        scores.update(validate(trainer, val_loader, model, criterion, args, metrics, tasks, epoch))
        is_best = scores[args.metric] > best_score
        best_score = max(scores[args.metric], best_score)
        checkpoints.save(epoch, args, model, optimizer, is_best, scores, args.metric) 

def __init__(self, args):
        cudnn.enabled = True
        self.args = args
        device = args.device
        student = Res_pspnet(BasicBlock, [2, 2, 2, 2], num_classes = args.classes_num)
        load_S_model(args, student, False)
        print_model_parm_nums(student, 'student_model')
        self.parallel_student = self.DataParallelModelProcess(student, 2, 'train', device)
        self.student = student

        teacher = Res_pspnet(Bottleneck, [3, 4, 23, 3], num_classes = args.classes_num)
        load_T_model(teacher, args.T_ckpt_path)
        print_model_parm_nums(teacher, 'teacher_model')
        self.parallel_teacher = self.DataParallelModelProcess(teacher, 2, 'eval', device)
        self.teacher = teacher

        D_model = Discriminator(args.preprocess_GAN_mode, args.classes_num, args.batch_size, args.imsize_for_adv, args.adv_conv_dim)
        load_D_model(args, D_model, False)
        print_model_parm_nums(D_model, 'D_model')
        self.parallel_D = self.DataParallelModelProcess(D_model, 2, 'train', device)

        self.G_solver = optim.SGD([{'params': filter(lambda p: p.requires_grad, self.student.parameters()), 'initial_lr': args.lr_g}], args.lr_g, momentum=args.momentum, weight_decay=args.weight_decay)
        self.D_solver = optim.SGD([{'params': filter(lambda p: p.requires_grad, D_model.parameters()), 'initial_lr': args.lr_d}], args.lr_d, momentum=args.momentum, weight_decay=args.weight_decay)

        self.best_mean_IU = args.best_mean_IU

        self.criterion = self.DataParallelCriterionProcess(CriterionDSN()) #CriterionCrossEntropy()
        self.criterion_pixel_wise = self.DataParallelCriterionProcess(CriterionPixelWise())
        #self.criterion_pair_wise_for_interfeat = [self.DataParallelCriterionProcess(CriterionPairWiseforWholeFeatAfterPool(scale=args.pool_scale[ind], feat_ind=-(ind+1))) for ind in range(len(args.lambda_pa))]
        self.criterion_pair_wise_for_interfeat = self.DataParallelCriterionProcess(CriterionPairWiseforWholeFeatAfterPool(scale=args.pool_scale, feat_ind=-5))
        self.criterion_adv = self.DataParallelCriterionProcess(CriterionAdv(args.adv_loss_type))
        if args.adv_loss_type == 'wgan-gp':
            self.criterion_AdditionalGP = self.DataParallelCriterionProcess(CriterionAdditionalGP(self.parallel_D, args.lambda_gp))
        self.criterion_adv_for_G = self.DataParallelCriterionProcess(CriterionAdvForG(args.adv_loss_type))
            
        self.mc_G_loss = 0.0
        self.pi_G_loss = 0.0
        self.pa_G_loss = 0.0
        self.D_loss = 0.0

        cudnn.benchmark = True
        if not os.path.exists(args.snapshot_dir):
            os.makedirs(args.snapshot_dir) 

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, CLASSES, args.layers, args.auxiliary, genotype)
  model = model.cuda()
  model.load_state_dict(torch.load(args.model_path)['state_dict'])

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

  criterion = nn.CrossEntropyLoss()
  criterion = criterion.cuda()

  validdir = os.path.join(args.data, 'val')
  normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  valid_data = dset.ImageFolder(
    validdir,
    transforms.Compose([
      transforms.Resize(256),
      transforms.CenterCrop(224),
      transforms.ToTensor(),
      normalize,
    ]))

  valid_queue = torch.utils.data.DataLoader(
    valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=4)

  model.drop_path_prob = args.drop_path_prob
  valid_acc_top1, valid_acc_top5, valid_obj = infer(valid_queue, model, criterion)
  logging.info('valid_acc_top1 %f', valid_acc_top1)
  logging.info('valid_acc_top5 %f', valid_acc_top5) 

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

    if args.auxiliary and args.net_type == 'macro':
        logging.info('auxiliary head classifier not supported for macro search space models')
        sys.exit(1)

    logging.info("args = %s", args)

    cudnn.enabled = True
    cudnn.benchmark = True
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    torch.cuda.manual_seed(args.seed)

    # Data
    _, valid_transform = utils._data_transforms_cifar10(args)

    valid_data = torchvision.datasets.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)

    # classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

    # Model
    if args.net_type == 'micro':
        logging.info("==> Building micro search space encoded architectures")
        genotype = eval("genotypes.%s" % args.arch)
        net = PyrmNASNet(args.init_channels, num_classes=10, layers=args.layers,
                         auxiliary=args.auxiliary, genotype=genotype,
                         increment=args.filter_increment, SE=args.SE)
    elif args.net_type == 'macro':
        genome = eval("macro_genotypes.%s" % args.arch)
        channels = [(3, 128), (128, 128), (128, 128)]
        net = EvoNetwork(genome, channels, 10, (32, 32), decoder='dense')
    else:
        raise NameError('Unknown network type, please only use supported network type')

    # logging.info("{}".format(net))
    logging.info("param size = %fMB", utils.count_parameters_in_MB(net))

    net = net.to(device)
    # no drop path during inference
    net.droprate = 0.0
    utils.load(net, args.model_path)

    criterion = nn.CrossEntropyLoss()
    criterion.to(device)

    # inference on original CIFAR-10 test images
    infer(valid_queue, net, criterion)