Faster MNIST.md

Now available here: https://github.com/y0ast/pytorch-snippets/tree/main/fast_mnist

Unfortunately that does not give the correct behavior: you're not randomizing your batches at each epoch which leads to significant reduced performance.

Yes this normalization is 0 mean, 1 std, for a VAE + MNIST you generally model your data as a multivariate bernoulli, which requires it to be between 0 and 1.

Unfortunately that does not give the correct behavior: you're not randomizing your batches at each epoch which leads to significant reduced performance.

That's true, the shuffling should then be done manually. I think this should work:

train_dataset.data = train_dataset.data[torch.randperm(train_dataset.data.shape[0])]

(assuming the first dimension of train_dataset.data to be the batch size)