Add ModelInputWrapper class to feed inputs to pytorch modules for layer methods #534
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
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
miguelmartin75
changed the title
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 8, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: c46f1f720132edc674ccc12a2268ddb68b6d9af8
miguelmartin75
force-pushed
the
export-D25110896
branch
from
59168bd
to
6c889cd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 8, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: cffb280e58f29725c5115c9088160bdeedf58ef3
miguelmartin75
force-pushed
the
export-D25110896
branch
from
6c889cd
to
bc9c9cb
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 8, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 1f640f0ad90f02829c1f7afdd1d6c167323ec92a
miguelmartin75
force-pushed
the
export-D25110896
branch
from
bc9c9cb
to
9ef7845
Compare
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 9, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 7a28a719e1a403f507650d454272be2caba3624c
miguelmartin75
force-pushed
the
export-D25110896
branch
from
9ef7845
to
b199a66
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 9, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 3976e3a9d2251523b8255a85e190916e8f5a6ca4
miguelmartin75
force-pushed
the
export-D25110896
branch
from
b199a66
to
27804a9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 10, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: c5e4d82895d26b302d55d1785f26ae3b194ae9d2
miguelmartin75
force-pushed
the
export-D25110896
branch
from
27804a9
to
2d4492f
Compare
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 11, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 51ae4c2fda32f12d5c23bb0d278ed284b0288347
miguelmartin75
force-pushed
the
export-D25110896
branch
from
2d4492f
to
a7e59b4
Compare
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 11, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 1744f083a0188b5dc54d93d2d210113b28acf233
miguelmartin75
force-pushed
the
export-D25110896
branch
from
a7e59b4
to
6de458c
Compare
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 11, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: 1d951bf06510aab85f83d4484ed8fabb724356c5
miguelmartin75
force-pushed
the
export-D25110896
branch
from
6de458c
to
4052a19
Compare
miguelmartin75
added a commit
to miguelmartin75/captum
that referenced
this pull request
Dec 11, 2020
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Differential Revision: D25110896 fbshipit-source-id: e71d520d5984b7d046ac5ab0b658d367398cf53b
miguelmartin75
force-pushed
the
export-D25110896
branch
from
4052a19
to
992887a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
Summary: Pull Request resolved: pytorch#534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Reviewed By: NarineK Differential Revision: D25110896 fbshipit-source-id: 82b6a4c335904833089b6c0e731d4fdd716163a2
miguelmartin75
force-pushed
the
export-D25110896
branch
from
992887a
to
0c4f83c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25110896 |
|
This pull request has been merged in 174ecbd. |
vivekmig
pushed a commit
that referenced
this pull request
Jan 21, 2021
Summary: Pull Request resolved: #534 Introduces a utility class called `ModelInputWrapper` to wrap over a model in order to treat inputs as separate layers. This does so by mapping each input fed to `forward` using an `Identity` operation. This way if attribute_to_inputs=True or False it should work. Add two tests: - Test whether _foward_layer_eval retrieves the appropriate input values - Compare regular IG with layer IG and layer wrapped inputs Updated tutorial and documentation Reviewed By: NarineK Differential Revision: D25110896 fbshipit-source-id: bb8dd4947ae88e183af94c09cf906f9687fbe8ff
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:
Introduces a utility class called
ModelInputWrapperto wrap over a model in order to treat inputs as separate layers.This does so by mapping each input fed to
forwardusing anIdentityoperation. This way if attribute_to_inputs=True or False it should work.Add two tests:
Differential Revision: D25110896