Optim-wip: Add Activation Atlas sample collection tutorial & supporting code #750
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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 theOptional
type hint and theMaxPool2dRelaxed
class at the bottom of the file.