noegroup/stochastic_normalizing_flows

Stochastic Normalizing Flows

stochastic_normalizing_flows's Issues

LICENSE for repository

Thanks for open sourcing this code. I would be interested in trying it out at DeepMind, but it makes it difficult unless the license is specified in the repository. If that is something you are able to do, it is most straightforward if you put in a LICENSE file. I can try if it has for instance Apache 2.0 or MIT though of course I can't advise you what license works best in your case. At DeepMind we use Apache 2.0. Happy to discuss further. Thanks very much,
Alex

Reproducing LangevinVAE result in Table 3

Thanks for your insightful paper and sharing code.

I run your shared code on experiment 4 MNIST, I can reproduce results claimed in Table 3 except LangevinVAE. It reported NLL around 200 in multiple runs.

I notice there could be a bug in your code, the line misses y in calling interpolated_force. But the results didn't change even I changed to

x1 = x + stepsize * self.interpolated_force(x, y, lambda_) + torch.sqrt(2*stepsize) * torch.randn_like(x)