Nathan

Hi there, MNIST is not specifically a disentanglement dataset. I would be hesitant to add it to disent because of this, also because there are many existing dataset loaders for...

Fixed optimiser pickling in 82fa093adaac2d9d0fb9f56168af2c0b5a073872 TODO: add [checkpointing](https://pytorch-lightning.readthedocs.io/en/stable/common/weights_loading.html)

This will be easier now that metrics use the `@metric` decorator

partial implementation of tests in 7f7d757133bc483e4637be8ee57b86b0bc22e116 release v0.1.0 - metrics - samplers (old datasets) Tests for actual data is annoying, rather need to test the individual components of mock datasets.

Partial implementation of tests for - Hydra Experiments - Models

Interesting, they should be downloaded automatically. Did you specify `prepare=True`? If the above does not work, are you able to manually download the files into the directory it wants? I...

I noticed the color and shape MPI3D ground-truth factors were wrong due to a data loading error. - If you are still using MPI3D, please use `pip install disent==0.6.0`, I...

"Loss reduction mode" should maybe be called "beta scaling" and be a boolean value? - This takes inspiration from the original BetaVAE paper if I am not mistaken. The problem...

Also references to `\bibliography{example_refs}` do not seem to be included either, ie. linking to `/example_refs.bib`. In this case it doesn't even seem to work in the root dir.

That sounds ideal. I am not sure about the internals of the library, but I imagine this could have implications for the various helper methods and functions? I am not...