Mayukh Deb

@ProGamerGov Thank you so much for your help! I'll surely drop a message if I need some more help with this :) I'm working on [torch-dreams](https://github.com/Mayukhdeb/torch-dreams). It aims to be...

> Goal of the issue is to fix the bug in padding calculation logic for pooling layers. Due to miscalculation of padding shapes of layers are miscalculated leading to failure...

The process is formally described below :arrow_down: : 

Fast Noisegrad: The idea is just to add multiplicative noise to the model weights on each optimisation iteration -- but each time to the original model weights. Thus not stacking...

Hello @dkrako, Thanks for the PR 🙂 Highly appreciate the detailed notes as well! I will take a look at this and get back to you ASAP. Thanks again!

Hello @dkrako, Could you please provide more details on the exact use-case for these new components to help me better understand the PR? A Colab notebook or a reproducible snippet...

@dkrako what is the shape of the tensor that your model expects for time series images? If you can describe the problem in-detail, I can help you debug this on...

I've tried to make some progress on this recently, but it's not working as expected yet. You can find my prototype here: https://github.com/abraham-ai/eden/commit/5fb1cdd893179c732da808fa0bc1dfed4a447ff0

Hi @yeongjoonJu👋 -- Thanks for pointing out the issue ^^ > Even neuron id is different There was a typo in the index there, I will correct it. It was...

Also the following points might be useful as to why this issue might be occuring: - we are using the [umap](https://github.com/lmcinnes/umap) module as seen here https://github.com/lapalap/dora/blob/101190bc0b5607d05c54992f4e237a159327c594/dora/outlier_detection.py#L22 which does have some...