A possible typo in train.py

[csy530216]

In train.py, Line 61 to 68:

    train_transform = transforms.Compose([ # refer to https://pytorch.org/docs/stable/torchvision/transforms.html for more build-in online data augmentation
        transforms.Resize([int(128 * INPUT_SIZE[0] / 112), int(128 * INPUT_SIZE[0] / 112)]), # smaller side resized
        transforms.RandomCrop([INPUT_SIZE[0], INPUT_SIZE[1]]),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(mean = RGB_MEAN,
                             std = RGB_STD),
    ])

In Line 62, transforms.Resize([int(128 * INPUT_SIZE[0] / 112), int(128 * INPUT_SIZE[0] / 112)]) should be transforms.Resize([int(128 * INPUT_SIZE[0] / 112), int(128 * INPUT_SIZE[1] / 112)]).