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

global reasoning unit #181

Conversation

stephenyan1231
Copy link
Contributor

Summary:

  • Implement Global Reasoning Networks (glore) (https://arxiv.org/abs/1811.12814). The reference implementation is on Github (https://github.com/facebookresearch/GloRe)
  • Rename the json configs to tell whether glore is on or off. Therefore
    • train_kinetics400_glore_off_i3d50 means glore is off, but we use the baseline I3D-50 model in glore paper.
    • train_kinetics400_glore_on_i3d50 means glore is on and glore units are inserted into baseline I3D-50 model.
    • Similar changes are made to SlowFast sf json config. Since we only implement baseline I3D model used in SF, which is a slightly different I3D model from I3D model in glore, it is always off.

Differential Revision: D18344566

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 6, 2019
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

Summary:
Pull Request resolved: facebookresearch/ClassyVision#181

- Implement Global Reasoning Networks (`glore`) (https://arxiv.org/abs/1811.12814). The reference implementation is on Github (https://github.com/facebookresearch/GloRe)

- For now, we don't plan to open source `glore`. Thus, we implement a `ProdResNeXt3D` model in `prod_resnext3d.py`. Refactor `ResNeXt3D` to reduce the duplicate code between `ResNeXt3D` and `ProdResNeXt3D`.
   - In the long-run, we are more flexible to add more implementation to `ProdResNeXt3D` to meet prod needs while keeping the open source `ResNeXt3D` implementation minimal.

- Rename the json configs to tell whether glore is `on` or `off`. Therefore
  - `train_kinetics400_glore_off_i3d50` means `glore` is off, but we use the baseline I3D-50 model in `glore` paper.
  - `train_kinetics400_glore_on_i3d50` means `glore` is on and `glore` units are inserted into baseline I3D-50 model.
  - Similar changes are made to SlowFast `sf` json config. Since we only implement baseline I3D model used in SF, which is a slightly different I3D model from I3D model in `glore`, it is always `off`.

Reviewed By: vreis

Differential Revision: D18344566

fbshipit-source-id: fac0fe090f7814e5aa41d5be5ff29f198147a27d
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D18344566

facebook-github-bot pushed a commit that referenced this pull request Nov 7, 2019
Summary:
Pull Request resolved: #181

- Implement Global Reasoning Networks (`glore`) (https://arxiv.org/abs/1811.12814). The reference implementation is on Github (https://github.com/facebookresearch/GloRe)

- For now, we don't plan to open source `glore`. Thus, we implement a `ProdResNeXt3D` model in `prod_resnext3d.py`. Refactor `ResNeXt3D` to reduce the duplicate code between `ResNeXt3D` and `ProdResNeXt3D`.
   - In the long-run, we are more flexible to add more implementation to `ProdResNeXt3D` to meet prod needs while keeping the open source `ResNeXt3D` implementation minimal.

- Rename the json configs to tell whether glore is `on` or `off`. Therefore
  - `train_kinetics400_glore_off_i3d50` means `glore` is off, but we use the baseline I3D-50 model in `glore` paper.
  - `train_kinetics400_glore_on_i3d50` means `glore` is on and `glore` units are inserted into baseline I3D-50 model.
  - Similar changes are made to SlowFast `sf` json config. Since we only implement baseline I3D model used in SF, which is a slightly different I3D model from I3D model in `glore`, it is always `off`.

Reviewed By: vreis

Differential Revision: D18344566

fbshipit-source-id: ccf27f732a0839d3dfe93afb54c9ce05d1833cf6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants