Kwan Ho Ryan Chan

Hi, I would make sure that Z is normalized before you put it through the loss function. Another possibility is the number of classes is not set correctly. I would...

You have asked a really important question about scalability. Sadly I don't have a good answer for you for now, but our group is currently working on it. We will...

No worries about the delay! I am happy to keep updating my current implementation with the newest codebase you have at `master`. For instance, I see that you just added...

I have updated the code such that it uses the multi-layer `LayerActivation()` code. What other updates should I add to my code to match the contribution guidelines? Thanks~

Hey @vivekmig, thank you for the feedback! And don't worry about the delays. Once I have everything fixed up and added, I'll let you know again in this thread.

Sorry I got caught up with some of my other projects this past month. I am aiming to finish updating this pull request by the end of this month. Is...

Hi @vivekmig, I recently updated the `captum/attr/_core/multiscale_fast_cam.py` file based on your suggestions from above. In short, these are the changes: 1. I added the Gaussian normalization method, and made it...

Sorry I don't have a cleaned up version of that part for now. Can you email me and I can share and discuss the code with you privately? Thank you!

I was installing the conda environment on my mac, which is a Linux environment. I am guessing that the packages you listed are the underlying dependencies that common packages like...

I believe when I did the experiment, I was doing them on my macbook, so it was os-x only. Though I think I didn't use anything fancy, nothing other than...