LayerDeepLift Hook Fix #415
Closed
Conversation
This file contains 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
NarineK
approved these changes
Jun 25, 2020
captum/attr/_core/deep_lift.py
Outdated
| @@ -496,8 +496,10 @@ def _can_register_hook(self, module: Module) -> bool: | |||
| or not self._is_non_linear(module) | |||
| ) | |||
|
|
|||
| def _register_hooks(self, module: Module) -> None: | |||
| if not self._can_register_hook(module): | |||
| def _register_hooks(self, module: Module, skip_target_layer: bool = False) -> None: | |||
There was a problem hiding this comment.
nit: target layer can be confusing because we also have target output. Perhaps, we can use the same naming for attributing to input or output. attribute_to_layer_input=True
There was a problem hiding this comment.
@vivekmig has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
There was a problem hiding this comment.
@vivekmig has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
There was a problem hiding this comment.
@vivekmig has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
NarineK
pushed a commit
to NarineK/captum-1
that referenced
this pull request
Nov 19, 2020
Summary: This avoids adding a hook to the target layer non-linearity when using LayerDeepLift if attributing with respect to layer output. This fixes an issue with in-place modules caused by skipping cloning and adds a corresponding test case. Pull Request resolved: pytorch#415 Reviewed By: edward-io Differential Revision: D22241851 Pulled By: vivekmig fbshipit-source-id: 771a7cbb3cf77438bba901237defe937a26c415c
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This avoids adding a hook to the target layer non-linearity when using LayerDeepLift if attributing with respect to layer output. This fixes an issue with in-place modules caused by skipping cloning and adds a corresponding test case.