Add Method to check if output has valid shape for perturbations per eval. #1666
+185
−64
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
cyrjano
force-pushed
the
export-D86976520
branch
from
bc3c609 to
324eaae
Compare
cyrjano
added a commit
to cyrjano/captum
that referenced
this pull request
Nov 13, 2025
…val. (meta-pytorch#1666) Summary: This diff adds a new method to the `captum.attr._core.feature_ablation` module to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size. Differential Revision: D86976520
cyrjano
added a commit
to cyrjano/captum
that referenced
this pull request
Nov 13, 2025
…val. (meta-pytorch#1666) Summary: This diff adds a new method to the `captum.attr._core.feature_ablation` module to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size. Differential Revision: D86976520
cyrjano
force-pushed
the
export-D86976520
branch
from
324eaae to
052f277
Compare
cyrjano
added a commit
to cyrjano/captum
that referenced
this pull request
Nov 14, 2025
…val. (meta-pytorch#1666) Summary: This diff adds a new method to the `captum.attr._core.feature_ablation` module to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size. Differential Revision: D86976520
cyrjano
force-pushed
the
export-D86976520
branch
2 times, most recently
from
3804e56 to
489d6b8
Compare
cyrjano
added a commit
to cyrjano/captum
that referenced
this pull request
Nov 14, 2025
…val. (meta-pytorch#1666) Summary: This diff adds a new method to the `captum.attr._core.feature_ablation` module to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size. Differential Revision: D86976520
…val. (meta-pytorch#1666) Summary: This diff adds a new method to the `captum.attr._core.feature_ablation` module to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size. Differential Revision: D86976520
cyrjano
force-pushed
the
export-D86976520
branch
from
489d6b8 to
19e6367
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Summary: This diff adds a new method to the
captum.attr._core.feature_ablationmodule to check if the output shape of the forward function scales correctly with the input batch size when perturbations are applied. The method takes in the inputs, the number of examples, the initial evaluation, the modified evaluation, and the number of perturbations per evaluation as arguments. It then validates that the output shape of the forward function scales correctly with the input batch size.Differential Revision: D86976520