Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add ResNet MCMC baselines from SGMCMC paper #161

Open
dustinvtran opened this issue Sep 15, 2020 · 1 comment
Open

Add ResNet MCMC baselines from SGMCMC paper #161

dustinvtran opened this issue Sep 15, 2020 · 1 comment
Labels

Comments

@dustinvtran
Copy link
Member

dustinvtran commented Sep 15, 2020

@jereliu @flwenzel. One potential issue is that @flwenzel's SGMCMC paper was on the older Edward2 ResNet-20 baseline script (which itself was loosely based on the UQ benchmark's). This is before we upgraded to WRN-28-10.

@znado Not sure what we want to do with the resnet-20 baselines. We could have a separate directory in the CIFAR baselines for it if we'd like.

@dustinvtran dustinvtran added the p2 label Sep 15, 2020
@Jordy-VL
Copy link

@dustinvtran @znado Is there any concrete plan to make SG-MCMC and SG-HMC implementations in TensorFlow?

I have only found some implementations in Pytorch, but they might help in conversion: https://github.com/reml-lab/URSABench/blob/master/URSABench/inference/sghmc.py

Thanks in advance for the reply!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants