swa_gaussian
swa_gaussian copied to clipboard
wjmaddox
Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"
I couldn't many implementations for KFACLaplace so I was implementing it from your baseline in this repo. I noticed a few things about the handling of batchnorm that I am...
Hi @wjmaddox! I've been trying to reproduce the results for the segmentation experiment and have hit an error I cannot seem to fix. I'm using the commands in the readme...
Hi i have trained CIFAR10 with --split_classes 0 and after i have run /experiments/uncertainty/uncertainty.py i cannot understand the output about accuracy and NLL: I am expected different result with higher...
Hi Wesley (@wjmaddox) I was wondering if you could shed some light on the calibration plots. So I'm running the save calibration plots script giving as input the predictions and...
Bumps [scipy](https://github.com/scipy/scipy) from 1.1.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Hi again, I am trying to reproduce the UCI Regression experiments., specifically Table 12 from your paper. Do you have the executable setup available to rerun experiments for the SGD...
Thanks for open sourcing the code and the interesting paper. I am looking for the RMSE on UCI Regression experiments, as you state in 5.5 of the paper "We report...
Hi, and thank you for the great work. I'd like to compare some of your results with my own work and need access to either the model saves or, even...
Hello, I wanted to check the uncertainty properties of my SWAG models and can not reproduce the values from the paper. When I train a VGG16/CIFAR10 model with the parameters...
