Sean Welleck

Sorry about that, this is messy and needs refactoring - it's actually calling the `@property` `self.images`, which is actually just defined as `self._images`

We ended up using the `train()` function for the experiments, and the `train_simple` wasn't updated as the code evolved, so `train_simple` probably doesn't work right now. In `train()`, the training...

Regarding the multiple encoders, we were trying to measure the performance difference between using a simple encoder and three types of normalizing flows ('residual', householder, inverse autoregressive), while keeping everything...

I see, thanks. Right - we didn't use the conv net since we were just testing on MNIST, but in general it could be good to use. However, I don't...