Python torchvision.datasets.CIFAR100 Examples

def dataLoader(is_train=True, cuda=True, batch_size=64, shuffle=True):
        if is_train:
            trans = [transforms.RandomHorizontalFlip(),
                     transforms.RandomCrop(32, padding=4),
                     transforms.ToTensor(),
                     transforms.Normalize(mean=[n/255.
                        for n in [129.3, 124.1, 112.4]], std=[n/255. for n in [68.2,  65.4,  70.4]])]
            trans = transforms.Compose(trans)
            train_set = td.CIFAR100('data', train=True, transform=trans)
            size = len(train_set.train_labels)
            train_loader = torch.utils.data.DataLoader(
                            train_set, batch_size=batch_size, shuffle=shuffle)
        else:
            trans = [transforms.ToTensor(),
                     transforms.Normalize(mean=[n/255.
                        for n in [129.3, 124.1, 112.4]], std=[n/255. for n in [68.2,  65.4,  70.4]])]
            trans = transforms.Compose(trans)
            test_set = td.CIFAR100('data', train=False, transform=trans)
            size = len(test_set.test_labels)
            train_loader = torch.utils.data.DataLoader(
                            test_set, batch_size=batch_size, shuffle=shuffle)

        return train_loader, size 

def get_dataset(self):
        """
        Uses torchvision.datasets.CIFAR100 to load dataset.
        Downloads dataset if doesn't exist already.
        Returns:
             torch.utils.data.TensorDataset: trainset, valset
        """

        trainset = datasets.SVHN('datasets/SVHN/train/', split='train', transform=self.train_transforms,
                                 target_transform=None, download=True)
        valset = datasets.SVHN('datasets/SVHN/test/', split='test', transform=self.val_transforms,
                               target_transform=None, download=True)
        extraset = datasets.SVHN('datasets/SVHN/extra', split='extra', transform=self.train_transforms,
                                 target_transform=None, download=True)

        trainset = torch.utils.data.ConcatDataset([trainset, extraset])

        return trainset, valset 

def get_dataset(self):
        """
        Uses torchvision.datasets.CIFAR100 to load dataset.
        Downloads dataset if doesn't exist already.
        Returns:
             torch.utils.data.TensorDataset: trainset, valset
        """

        trainset = datasets.SVHN('datasets/SVHN/train/', split='train', transform=self.train_transforms,
                                 target_transform=None, download=True)
        valset = datasets.SVHN('datasets/SVHN/test/', split='test', transform=self.val_transforms,
                               target_transform=None, download=True)
        extraset = datasets.SVHN('datasets/SVHN/extra', split='extra', transform=self.train_transforms,
                                 target_transform=None, download=True)

        trainset = torch.utils.data.ConcatDataset([trainset, extraset])

        return trainset, valset 

def test():
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def __init__(self):
        super(CIFAR100MetaInfo, self).__init__()
        self.label = "CIFAR100"
        self.root_dir_name = "cifar100"
        self.dataset_class = CIFAR100Fine
        self.num_classes = 100 

def __init__(self, opt):
        """Initialize this dataset class.

        Parameters:
            opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions

        A few things can be done here.
        - save the options (have been done in BaseDataset)
        - get image paths and meta information of the dataset.
        - define the image transformation.
        """
        # save the option and dataset root
        BaseDataset.__init__(self, opt)
        # define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
        self.transform = get_transform(opt)
        
        # import torchvision dataset
        if opt.dataset_name == 'CIFAR10':
            from torchvision.datasets import CIFAR10 as torchvisionlib
        elif opt.dataset_name == 'CIFAR100':
            from torchvision.datasets import CIFAR100 as torchvisionlib
        else:
            raise ValueError('torchvision_dataset import fault.')

        self.dataload = torchvisionlib(root = opt.download_root,
                                       transform = self.transform,
                                       download = True) 

def build_cifar100(model_state_dict=None, optimizer_state_dict=None, **kwargs):
    epoch = kwargs.pop('epoch')
    ratio = kwargs.pop('ratio')
    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=train_transform)
    valid_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=valid_transform)

    num_train = len(train_data)
    assert num_train == len(valid_data)
    indices = list(range(num_train))    
    split = int(np.floor(ratio * num_train))
    np.random.shuffle(indices)

    train_queue = torch.utils.data.DataLoader(
        train_data, batch_size=args.child_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
        pin_memory=True, num_workers=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.child_eval_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:num_train]),
        pin_memory=True, num_workers=16)
    
    model = NASWSNetworkCIFAR(args, 100, args.child_layers, args.child_nodes, args.child_channels, args.child_keep_prob, args.child_drop_path_keep_prob,
                       args.child_use_aux_head, args.steps)
    model = model.cuda()
    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.child_lr_max,
        momentum=0.9,
        weight_decay=args.child_l2_reg,
    )
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)
    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, args.child_epochs, args.child_lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def build_cifar100(model_state_dict, optimizer_state_dict, **kwargs):
    epoch = kwargs.pop('epoch')

    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(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=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.eval_batch_size, shuffle=False, pin_memory=True, num_workers=16)
    
    model = NASNetworkCIFAR(args, 100, args.layers, args.nodes, args.channels, args.keep_prob, args.drop_path_keep_prob,
                       args.use_aux_head, args.steps, args.arch)
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
    logging.info("multi adds = %fM", model.multi_adds / 1000000)
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)

    if torch.cuda.device_count() > 1:
        logging.info("Use %d %s", torch.cuda.device_count(), "GPUs !")
        model = nn.DataParallel(model)
    model = model.cuda()

    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    
    optimizer = torch.optim.SGD(
        model.parameters(),
        args.lr_max,
        momentum=0.9,
        weight_decay=args.l2_reg,
    )
    
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)

    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs), args.lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def build_cifar100(model_state_dict, optimizer_state_dict, **kwargs):
    epoch = kwargs.pop('epoch')

    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=train_transform)
    valid_data = dset.CIFAR100(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=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.eval_batch_size, shuffle=False, pin_memory=True, num_workers=16)
    
    model = NASNetworkCIFAR(args, 100, args.layers, args.nodes, args.channels, args.keep_prob, args.drop_path_keep_prob,
                       args.use_aux_head, args.steps, args.arch)
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
    logging.info("multi adds = %fM", model.multi_adds / 1000000)
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)

    if torch.cuda.device_count() > 1:
        logging.info("Use %d %s", torch.cuda.device_count(), "GPUs !")
        model = nn.DataParallel(model)
    model = model.cuda()

    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    
    optimizer = torch.optim.SGD(
        model.parameters(),
        args.lr_max,
        momentum=0.9,
        weight_decay=args.l2_reg,
    )
    
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)

    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs), args.lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def build_cifar100(model_state_dict=None, optimizer_state_dict=None, **kwargs):
    epoch = kwargs.pop('epoch')
    ratio = kwargs.pop('ratio')
    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=train_transform)
    valid_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=valid_transform)

    num_train = len(train_data)
    assert num_train == len(valid_data)
    indices = list(range(num_train))    
    split = int(np.floor(ratio * num_train))
    np.random.shuffle(indices)

    train_queue = torch.utils.data.DataLoader(
        train_data, batch_size=args.child_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
        pin_memory=True, num_workers=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.child_eval_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:num_train]),
        pin_memory=True, num_workers=16)
    
    model = NASWSNetworkCIFAR(100, args.child_layers, args.child_nodes, args.child_channels, args.child_keep_prob, args.child_drop_path_keep_prob,
                       args.child_use_aux_head, args.steps)
    model = model.cuda()
    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.child_lr_max,
        momentum=0.9,
        weight_decay=args.child_l2_reg,
    )
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)
    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, args.child_epochs, args.child_lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def build_cifar100(model_state_dict, optimizer_state_dict, **kwargs):
    epoch = kwargs.pop('epoch')

    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(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=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.eval_batch_size, shuffle=False, pin_memory=True, num_workers=16)
    
    model = NASNetworkCIFAR(args, 100, args.layers, args.nodes, args.channels, args.keep_prob, args.drop_path_keep_prob,
                       args.use_aux_head, args.steps, args.arch)
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
    logging.info("multi adds = %fM", model.multi_adds / 1000000)
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)

    if torch.cuda.device_count() > 1:
        logging.info("Use %d %s", torch.cuda.device_count(), "GPUs !")
        model = nn.DataParallel(model)
    model = model.cuda()

    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    
    optimizer = torch.optim.SGD(
        model.parameters(),
        args.lr_max,
        momentum=0.9,
        weight_decay=args.l2_reg,
    )
    
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)

    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs), args.lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def __init__(self, options):
        transform_list = []
        if options.image_size is not None:
            transform_list.append(transforms.Resize((options.image_size, options.image_size)))
            # transform_list.append(transforms.CenterCrop(options.image_size))
        transform_list.append(transforms.ToTensor())
        if options.image_colors == 1:
            transform_list.append(transforms.Normalize(mean=[0.5], std=[0.5]))
        elif options.image_colors == 3:
            transform_list.append(transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]))
        transform = transforms.Compose(transform_list)

        if options.dataset == 'mnist':
            dataset = datasets.MNIST(options.data_dir, train=True, download=True, transform=transform)
        elif options.dataset == 'emnist':
            # Updated URL from https://www.westernsydney.edu.au/bens/home/reproducible_research/emnist
            datasets.EMNIST.url = 'https://cloudstor.aarnet.edu.au/plus/s/ZNmuFiuQTqZlu9W/download'
            dataset = datasets.EMNIST(options.data_dir, split=options.image_class, train=True, download=True, transform=transform)
        elif options.dataset == 'fashion-mnist':
            dataset = datasets.FashionMNIST(options.data_dir, train=True, download=True, transform=transform)
        elif options.dataset == 'lsun':
            training_class = options.image_class + '_train'
            dataset =  datasets.LSUN(options.data_dir, classes=[training_class], transform=transform)
        elif options.dataset == 'cifar10':
            dataset = datasets.CIFAR10(options.data_dir, train=True, download=True, transform=transform)
        elif options.dataset == 'cifar100':
            dataset = datasets.CIFAR100(options.data_dir, train=True, download=True, transform=transform)
        else:
            dataset = datasets.ImageFolder(root=options.data_dir, transform=transform)

        self.dataloader = DataLoader(
            dataset,
            batch_size=options.batch_size,
            num_workers=options.loader_workers,
            shuffle=True,
            drop_last=True,
            pin_memory=options.pin_memory
        )
        self.iterator = iter(self.dataloader) 

def get_dataset(name, split='train', transform=None,
                target_transform=None, download=True, datasets_path=__DATASETS_DEFAULT_PATH):
    train = (split == 'train')
    root = os.path.join(datasets_path, name)
    if name == 'cifar10':
        return datasets.CIFAR10(root=root,
                                train=train,
                                transform=transform,
                                target_transform=target_transform,
                                download=download)
    elif name == 'cifar100':
        return datasets.CIFAR100(root=root,
                                 train=train,
                                 transform=transform,
                                 target_transform=target_transform,
                                 download=download)
    elif name == 'mnist':
        return datasets.MNIST(root=root,
                              train=train,
                              transform=transform,
                              target_transform=target_transform,
                              download=download)
    elif name == 'stl10':
        return datasets.STL10(root=root,
                              split=split,
                              transform=transform,
                              target_transform=target_transform,
                              download=download)
    elif name == 'imagenet':
        if train:
            root = os.path.join(root, 'train')
        else:
            root = os.path.join(root, 'val')
        return datasets.ImageFolder(root=root,
                                    transform=transform,
                                    target_transform=target_transform) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=False, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def test(model):
    kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
    if args.dataset == 'cifar10':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR10('./data.cifar10', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    elif args.dataset == 'cifar100':
        test_loader = torch.utils.data.DataLoader(
            datasets.CIFAR100('./data.cifar100', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])),
            batch_size=args.test_batch_size, shuffle=True, **kwargs)
    else:
        raise ValueError("No valid dataset is given.")
    model.eval()
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = model(data)
        pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
        correct += pred.eq(target.data.view_as(pred)).cpu().sum()

    print('\nTest set: Accuracy: {}/{} ({:.1f}%)\n'.format(
        correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))
    return correct / float(len(test_loader.dataset)) 

def fetch_bylabel(label):
    if label == 10:
        normalizer = transforms.Normalize(mean=[0.4914, 0.4824, 0.4467],
                                          std=[0.2471, 0.2435, 0.2616])
        data_cls = datasets.CIFAR10
    else:
        normalizer = transforms.Normalize(mean=[0.5071, 0.4867, 0.4408],
                                          std=[0.2675, 0.2565, 0.2761])
        data_cls = datasets.CIFAR100
    return normalizer, data_cls 

def __init__(self, opt):
		kwargs = {
		  'num_workers': opt.workers,
		  'batch_size' : opt.batch_size,
		  'shuffle' : True,
		  'pin_memory': True}

		self.train_loader = torch.utils.data.DataLoader(
			datasets.CIFAR100(opt.data_dir, train=True, download=True,
					transform=transforms.Compose([
						transforms.RandomCrop(32, padding=4),
						transforms.RandomHorizontalFlip(),
						transforms.ToTensor(),
						transforms.Normalize(mean=[x/255.0 for x in [129.3, 124.1, 112.4]],
std=[x/255.0 for x in [68.2, 65.4, 70.4]])
					   ])),
			 **kwargs)

		self.val_loader = torch.utils.data.DataLoader(
			datasets.CIFAR100(opt.data_dir, train=False,
			  transform=transforms.Compose([
						   transforms.ToTensor(),
						   transforms.Normalize(mean=[x/255.0 for x in [129.3, 124.1, 112.4]],
std=[x/255.0 for x in [68.2, 65.4, 70.4]])
					   ])),
		  **kwargs) 

def build_cifar100(model_state_dict=None, optimizer_state_dict=None, **kwargs):
    epoch = kwargs.pop('epoch')
    ratio = kwargs.pop('ratio')
    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=train_transform)
    valid_data = dset.CIFAR100(root=args.data, train=True, download=True, transform=valid_transform)

    num_train = len(train_data)
    assert num_train == len(valid_data)
    indices = list(range(num_train))    
    split = int(np.floor(ratio * num_train))
    np.random.shuffle(indices)

    train_queue = torch.utils.data.DataLoader(
        train_data, batch_size=args.child_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
        pin_memory=True, num_workers=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.child_eval_batch_size,
        sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:num_train]),
        pin_memory=True, num_workers=16)
    
    model = NASWSNetworkCIFAR(100, args.child_layers, args.child_nodes, args.child_channels, args.child_keep_prob, args.child_drop_path_keep_prob,
                       args.child_use_aux_head, args.steps)
    model = model.cuda()
    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.child_lr_max,
        momentum=0.9,
        weight_decay=args.child_l2_reg,
    )
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)
    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, args.child_epochs, args.child_lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def build_cifar100(model_state_dict, optimizer_state_dict, **kwargs):
    epoch = kwargs.pop('epoch')

    train_transform, valid_transform = utils._data_transforms_cifar10(args.cutout_size)
    train_data = dset.CIFAR100(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=16)
    valid_queue = torch.utils.data.DataLoader(
        valid_data, batch_size=args.eval_batch_size, shuffle=False, pin_memory=True, num_workers=16)
    
    model = NASNetworkCIFAR(args, 100, args.layers, args.nodes, args.channels, args.keep_prob, args.drop_path_keep_prob,
                       args.use_aux_head, args.steps, args.arch)
    logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
    logging.info("multi adds = %fM", model.multi_adds / 1000000)
    if model_state_dict is not None:
        model.load_state_dict(model_state_dict)

    if torch.cuda.device_count() > 1:
        logging.info("Use %d %s", torch.cuda.device_count(), "GPUs !")
        model = nn.DataParallel(model)
    model = model.cuda()

    train_criterion = nn.CrossEntropyLoss().cuda()
    eval_criterion = nn.CrossEntropyLoss().cuda()
    
    optimizer = torch.optim.SGD(
        model.parameters(),
        args.lr_max,
        momentum=0.9,
        weight_decay=args.l2_reg,
    )
    
    if optimizer_state_dict is not None:
        optimizer.load_state_dict(optimizer_state_dict)

    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs), args.lr_min, epoch)
    return train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler 

def get_train_val_loaders(self):
        if self.args.dataset == 'cifar10':
            train_transform, valid_transform = utils._data_transforms_cifar10(self.args)
            train_data = dset.CIFAR10(
                root=self.args.data, train=True, download=True, transform=train_transform)
            valid_data = dset.CIFAR10(
                root=self.args.data, train=False, download=True, transform=valid_transform)
        elif self.args.dataset == 'cifar100':
            train_transform, valid_transform = utils._data_transforms_cifar100(self.args)
            train_data = dset.CIFAR100(
                root=self.args.data, train=True, download=True, transform=train_transform)
            valid_data = dset.CIFAR100(
                root=self.args.data, train=False, download=True, transform=valid_transform)
        elif self.args.dataset == 'svhn':
            train_transform, valid_transform = utils._data_transforms_svhn(self.args)
            train_data = dset.SVHN(
                root=self.args.data, split='train', download=True, transform=train_transform)
            valid_data = dset.SVHN(
                root=self.args.data, split='test', download=True, transform=valid_transform)

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

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

        return train_queue, valid_queue, train_transform, valid_transform 

def get_train_val_loaders(self):
        if self.args.dataset == 'cifar10':
            train_transform, valid_transform = utils._data_transforms_cifar10(self.args)
            train_data = dset.CIFAR10(root=self.args.data, train=True, download=True, transform=train_transform)
        elif self.args.dataset == 'cifar100':
            train_transform, valid_transform = utils._data_transforms_cifar100(self.args)
            train_data = dset.CIFAR100(root=self.args.data, train=True, download=True, transform=train_transform)
        elif self.args.dataset == 'svhn':
            train_transform, valid_transform = utils._data_transforms_svhn(self.args)
            train_data = dset.SVHN(root=self.args.data, split='train', download=True, transform=train_transform)

        num_train = len(train_data)
        indices = list(range(num_train))
        split = int(np.floor(self.args.train_portion * num_train))

        train_queue = torch.utils.data.DataLoader(
            train_data, batch_size=self.args.batch_size,
            sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[:split]),
            pin_memory=True, num_workers=2)

        valid_queue = torch.utils.data.DataLoader(
            train_data, batch_size=self.args.batch_size,
            sampler=torch.utils.data.sampler.SubsetRandomSampler(indices[split:num_train]),
            pin_memory=True, num_workers=2)

        return train_queue, valid_queue, train_transform, valid_transform