Dataset creation for pretrained alexnet model in pytorch.

image_dataset.py

root = 'imagenet'
traindir = 'train'
image_dataset = ImageFolder(
    traindir,
    transform=transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225]),
    ])
)