MH1996

Hey @AlphaBetaGamma96, thanks for your response. Unfortunately I do need running statistics as I am using stochastic weight averaging. When using the pytorch lightning module for SWA, for example, I...

@samdow Essentially what @AlphaBetaGamma96 has posted about the Hutchinson method is what I am using. During training I compute the trace of the Hessian every `n`-th step and then do...

Thanks for your quick response! It is quite hard to share my `f` actually because there is a whole lot going on. But here is the actual class that I...

This is basically the issue I have been trying to work out too (referring to the 3355 difference in parameters). To your points: - The optimizable parameters that I pass...

Hey, I was wondering if you had any more thoughts on this issue. I didn't have time in the last couple of weeks to work on it, but I am...

Hi @chr5tphr , thank you for providing this feature. I have been working with this version of Zennit to get relevance scores for w.r.t parameters. However, when using a ResNet20...

Hey @chr5tphr, thank you very much for you response, and your quick fix of `grad_sink`. Too bad about ResNet, but thanks for taking the time to work on it. Could...

I checked the outputs and they were not equal. I went back to check the ResNet20 I was using, and although it seemed like a pretty standard implementation, it had...