Incorrect loss for AutoEncoder

[ncoop57]

In computing the testing loss for the autoencoder, you reuse the training set

# test on holdout

loss = []
    for batch, test_x in tqdm(
        zip(range(N_TRAIN_BATCHES), train_dataset), total=N_TRAIN_BATCHES # Why is this using training again?
    ):

[timsainb]

Thanks for pointing this out, it looks like I did this for multiple models.

[ncoop57]

No problem. Thank you for this awesome set of models and straightforward code! It has greatly helped my understanding of these models, especially VAEs.