-
Notifications
You must be signed in to change notification settings - Fork 479
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
Conversation
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. Pull Request resolved: pytorch#1155 Differential Revision: D46322232 fbshipit-source-id: 1bb4c0bbd9b549332d3eb8455a8bf33065bf52dc
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. Pull Request resolved: pytorch#1155 Differential Revision: D46322232 fbshipit-source-id: 56d3d368424bffb78c7cb0e9c026f04b767ed195
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 Differential Revision: D46322232 fbshipit-source-id: 9398de2955d1d303467d4e4577eabb01642f86c5
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 Differential Revision: D46322232 fbshipit-source-id: d0c2119dd002105e54de97549f3717494baa1096
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 Differential Revision: D46322232 fbshipit-source-id: 38f901aabd029cda73c19ea513d1694fa54f83a9
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: 009aee61549d2b11d7c4f83ecc5cf9688e7993d6
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: acc99f6f662108a701a4e32152d905e07565c81f
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: fddb80aa0e2a5231bd7a62e568ed80e9ebc52a7f
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
This pull request was exported from Phabricator. Differential Revision: D46322232 |
This pull request has been merged in b1a9830. |
Differential Revision: D46322232