Transforms gives weird white image

[harshdhamecha]

We have used the following transformations in dataset_loader.py

from src.data_io import transform as trans

def get_train_loader(conf):
    train_transform = trans.Compose([
        trans.ToPILImage(),
        trans.RandomResizedCrop(size=tuple(conf.input_size),
                                scale=(0.9, 1.1)),
        trans.ColorJitter(brightness=0.4,
                          contrast=0.4, saturation=0.4, hue=0.1),
        trans.RandomRotation(10),
        trans.RandomHorizontalFlip(),
        trans.ToTensor()
    ])
    ... # (Just to shorten the code here)
    return train_loader

The resultant images before and after transforms were as follows:

Before

After

When we replace the src.data_io's transforms with torchvision's transforms and keeping the transform pipeline same, we get the following results:

Before

After

The torchvision's transforms gives desired results in our opinion. Correct us if we are wrong.

Is there anything wrong in our transform pipeline or the author had implemented this transform to improve liveness performance?

Please shed some lights on this!

Issue credit: @vrushank-pambhar