Skip to content

Conversation

ProGamerGov
Copy link
Contributor

@ProGamerGov ProGamerGov commented Sep 8, 2021

Refer to #579 for more details, this PR replaces #729

This PR adds the setup tutorial notebook for collecting the required sample activations and attributions for activation atlases from user supplied image datasets.

It also adds the required relaxed max pooling layer used to collect sample attributions. This layer was included in captum/optim/models/_common.py, so we can verify it works correctly for the tutorial.

For some reason Github thinks I changed the entire captum/optim/models/_common.py, when all I did was add the Optional type hint and the MaxPool2dRelaxed class at the bottom of the file.

@ProGamerGov ProGamerGov changed the title Add Activation Atlas sample collection tutorial & supporting code Optim-wip: Add Activation Atlas sample collection tutorial & supporting code Sep 8, 2021
@NarineK
Copy link
Contributor

NarineK commented Sep 23, 2021

Looks great! Thank you for working on this PR, @ProGamerGov!
Maybe you can address this one and we can get it merged: #729 (comment)

@NarineK NarineK self-requested a review September 23, 2021 21:56
@NarineK NarineK merged commit 6e7f0bd into pytorch:optim-wip Sep 27, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants