GitLab

It was pointing to an old version where the validation pre-processing was the same as the training pre-processing, and thus had randomness in it (instead of CenterCrop).

* EMNIST dataset + speedup *MNIST preprocessing

* add docs for grayscale + random grayscale transforms

added CIFAR100 autoclass in docs

PIL.Image is renamed to 'PIL Image' because PIL.Image is the module and PIL.Image.Image is the class we are referring but is too long to put in docstrings