Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add DataloaderAttribution #1155

Closed
wants to merge 1 commit into from
Closed

Conversation

aobo-y
Copy link
Contributor

@aobo-y aobo-y commented Jun 13, 2023

Differential Revision: D46322232

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 14, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

Pull Request resolved: pytorch#1155

Differential Revision: D46322232

fbshipit-source-id: 1bb4c0bbd9b549332d3eb8455a8bf33065bf52dc
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 14, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

Pull Request resolved: pytorch#1155

Differential Revision: D46322232

fbshipit-source-id: 56d3d368424bffb78c7cb0e9c026f04b767ed195
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 14, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Differential Revision: D46322232

fbshipit-source-id: 9398de2955d1d303467d4e4577eabb01642f86c5
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 15, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Differential Revision: D46322232

fbshipit-source-id: d0c2119dd002105e54de97549f3717494baa1096
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 15, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Differential Revision: D46322232

fbshipit-source-id: 38f901aabd029cda73c19ea513d1694fa54f83a9
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 22, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Reviewed By: vivekmig

Differential Revision: D46322232

fbshipit-source-id: 009aee61549d2b11d7c4f83ecc5cf9688e7993d6
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 22, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Reviewed By: vivekmig

Differential Revision: D46322232

fbshipit-source-id: acc99f6f662108a701a4e32152d905e07565c81f
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

aobo-y added a commit to aobo-y/captum that referenced this pull request Jun 22, 2023
Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Reviewed By: vivekmig

Differential Revision: D46322232

fbshipit-source-id: fddb80aa0e2a5231bd7a62e568ed80e9ebc52a7f
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

Summary:
Implement DataloaderAttribution, an attribution wrapper designed to wrap existing perturbation attr methods so that they can take `torch.utils.data.DataLoader` as the inputs. This enables attributions with respect to corpus-level metrics.

`perturbation_per_pass` is not supported in this diff. Will add separately in the next diff

Pull Request resolved: pytorch#1155

Reviewed By: vivekmig

Differential Revision: D46322232

fbshipit-source-id: 4f92159d9942272c883d32d412330b632cc4fd40
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D46322232

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in b1a9830.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants