TJ Torres

Any chance you might point me to sources? I have seen BCE used to more accurately reflect the distribution of the data when binary (for instance if training on the...

It definitely makes sense to add the Bernoulli negative log likelihood if one wishes to look at Bernoulli distributed posterior data distributions as in say MNIST, though I hadn't envisioned...

Sounds great! Should be quite fast to validate over MNIST, though I think the MNIST set will be too small to use with the convolution architecture currently available. MNIST images...

This looks good so far. I'll do some testing and then merge after.

Can you give me a bit more info as to how this error came about? Are you using the command line tools or one of the model classes? Have you...

No, I just forgot to update the version to bs4 in the setup file. Thanks for the bug report.