Concatenate two times train_set

[Elpidam]

Hello! Recently I noticed that in create_mnist_dataset.py, in line 24: all_digits = np.concatenate([mnist_data['X_train'], mnist_data['X_valid'], mnist_data['X_train']], axis=0)

the last part of the concatenation is train set as it was the first part. This might be a mistake. Right?

[skaae]

Yes i think you are correct. I don't think it mattes because i do only use that all_digits for generating a list of distortions.

I corrected the error. Thanks for pointing it out :)