normalizing-flows

normalizing-flows copied to clipboard

NormalizingFlow class in core.py does not provide context in forward_kld

3

Thank you for a repo that's easy to handle with a normalizing flow of one's choice! I would like to implement a normalizing flow that optimizes multiple target distributions at...

ybernaerts

Hi, this PR added some new interface to get better control during sampling, e.g. to repeatedly generate on same latent code when training the model. Please check if it is...

prclibo

Hi, I was trying to integrate your code in pytorch lightning framework and found that some scalar flag attributes caused exceptions when parallelizing the nn.Module. This PR removes it for...

prclibo

making data loading and iter works !

1

mbaddar1

Flow++

2

Hello! This is an excellent repository that I am using for my Ph.D. Thank you for such a fantastic contribution! I wonder if you have plans to develop Flow++ https://arxiv.org/abs/1902.00275....

mjack3

Hey, thanks for your framework. Are you currently planning to implement flows on spheres supporting forward and backward KLD as well? Thanks and all the best

odunkel

It seems that some layers do not support conditioning, like the affine coupling block. Would it be possible to extend this, as suggested in e.g. https://arxiv.org/pdf/1912.00042 ? Wouldn't be much...

rudolfwilliam

Newer setuptools version enforce the new syntax. Just a minor change

jonas-eschle

Hello guys, I have a question about the transformed distributions. Like we have a base density distribution like Indenpenden(Normal(mu, sigma)) after normalizing flows, how can I get the transformed distribution?...

ZhengtingJiang

Optimal hyperparameters and optimal flow design

3

Hello! Thank you for excellent framework! For my bachelor thesis I have to adapt SAILOR (Link to project: https://github.com/malicd/sailor). I should implement NF instead of Gaussian Mixture Model. Short about...

dodreh