Loss and Backprop Details

Hi,

During training the vqvae backprops on multiple losses. While inputting feature maps to the model, we are given a loss, shoud I manually backpropagate and update weights through (the good ol' loss.backward() and optimizer.step()) this or is it handled implicitly?

No file, test, or entry point is named. Start by reviewing the repository's VQ-VAE training usage and loss handling to determine whether callers must invoke backward() and optimizer.step(); done means documenting that behavior clearly.

Written by the indexing model from the issue text.