Add support for list of tensors output in Layer Gradient Attributor #1629
+24
−15
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
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
force-pushed
the
export-D79134965
branch
from
698d601 to
d9b908f
Compare
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Jul 29, 2025
…ytorch#1629) Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Differential Revision: D79134965
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Jul 30, 2025
…ytorch#1629) Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Differential Revision: D79134965
sharontanxh
force-pushed
the
export-D79134965
branch
from
d9b908f to
43cb1fe
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Jul 31, 2025
…ytorch#1629) Summary: Pull Request resolved: pytorch#1629 As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Differential Revision: D79134965
sharontanxh
force-pushed
the
export-D79134965
branch
2 times, most recently
from
f72b40f to
9262247
Compare
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Jul 31, 2025
…ytorch#1629) Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Differential Revision: D79134965
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Aug 7, 2025
…ytorch#1629) Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Reviewed By: craymichael Differential Revision: D79134965
sharontanxh
force-pushed
the
export-D79134965
branch
from
9262247 to
15e2e28
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Aug 7, 2025
…ytorch#1629) Summary: Pull Request resolved: pytorch#1629 As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Reviewed By: craymichael Differential Revision: D79134965
sharontanxh
force-pushed
the
export-D79134965
branch
from
15e2e28 to
21a7248
Compare
sharontanxh
pushed a commit
to sharontanxh/captum
that referenced
this pull request
Aug 8, 2025
…ytorch#1629) Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Reviewed By: craymichael Differential Revision: D79134965
sharontanxh
force-pushed
the
export-D79134965
branch
from
21a7248 to
09b7130
Compare
…ytorch#1629) Summary: Pull Request resolved: pytorch#1629 As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly. Reviewed By: craymichael Differential Revision: D79134965
|
This pull request was exported from Phabricator. Differential Revision: D79134965 |
sharontanxh
force-pushed
the
export-D79134965
branch
from
09b7130 to
508fdc8
Compare
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.
Summary: As part of increasing % of layers supported, we want to extend Layer Gradient Attributor to support List of Tensor with grad outputs. This is fairly safe since we already support Tuple of Tensor with grad outputs, and iteration across both types behaves similarly.
Differential Revision: D79134965