transform = transforms.Compose([
    transforms.RandomSizedCrop(224),
    transforms.RandomHorizontalFlip(),
    transforms.mx.ToNdArray(),
    transforms.mx.Normalize(mean = [ 0.485, 0.456, 0.406 ],
                            std  = [ 0.229, 0.224, 0.225 ]),
])

from mxbox import transforms, datasets, DataLoader
trans = transforms.Compose([
        transforms.mx.ToNdArray(), 
        transforms.mx.Normalize(mean = [ 0.485, 0.456, 0.406 ],
                                std  = [ 0.229, 0.224, 0.225 ]),
])
dataset = datasets.CIFAR10('~/.mxbox/cifar10', transform=trans, download=True)

batch_size = 32
feedin_shapes = {
    'batch_size': batch_size,
    'data': [mx.io.DataDesc(name='data', shape=(batch_size, 3, 32, 32), layout='NCHW')],
    'label': [mx.io.DataDesc(name='softmax_label', shape=(batch_size, ), layout='N')]
}
loader = DataLoader(dataset, feedin_shapes, threads=8, shuffle=True)

class TooYoungScape(mxbox.Dataset):
    def __init__(self, root, lst, transform=None):
        self.root = root
        with open(osp.join(root, lst), 'r') as fp:
            self.lst = [line.strip().split('\t') for line in fp.readlines()]
        self.transform = transform

    def __getitem__(self, index):
        img = self.pil_loader(osp.join(self.root, self.lst[index][0]))
        if self.transform is not None:
            img = self.transform(img)
        return {'data': img, 'softmax_label': img}

    def __len__(self):
        return len(self.lst)
        
dataset = TooYoungScape('~/.mxbox/TooYoungScape', "train.lst", transform=trans)
loader = DataLoader(dataset, feedin_shapes, threads=8, shuffle=True)

vgg = mxbox.models.vgg(num_classes=10, pretrained=True)
resnet = mxbox.models.resnet152(num_classes=10, pretrained=True)