1. 28 Sep, 2022 2 commits
    • Matthew Yu's avatar
      support pytorch checkpoint as teacher model using config · dc176d58
      Matthew Yu authored
      Summary:
      Pull Request resolved: https://github.com/facebookresearch/d2go/pull/371
      
      In a previous iteration of this diff, we were specifying the teacher model in the same config as the student model, something like:
      ```
      # config.py
      MODEL:
        FBNET_V2:
        ...
      DISTILLATION:
        TEACHER:
          MODEL:
            FBNET_V2:
            ...
            WEIGHTS: /path/to/teacher/weights
      ...
      ```
      
      This leads to some oddities in the code, like we have to have a default config that adds all the required keys in the distillation teacher model.
      
      In this diff, we just let the user supply a teacher config (and optionally runner_name and overwrite opts) and use the supplied runner to build the model:
      ```
      # new_config.py
      MODEL:
        FBNET_V2:
      ...
      DISTILLATION:
        TEACHER:
          CONFIG_FNAME: /path/to/teacher/config
          RUNNER_NAME:
      ...
      ```
      
      This should make it very easy to specify the teacher as the user could potentially just reuse the trained_config generated in d2go.
      
      Reviewed By: newstzpz
      
      Differential Revision: D37640041
      
      fbshipit-source-id: 088a636c96f98279c9a04e32d1674f703451aec3
      dc176d58
    • Zhanibek Datbayev's avatar
      add assert for fb_overwritable decorator. · fce2a186
      Zhanibek Datbayev authored
      Summary:
      X-link: https://github.com/facebookresearch/mobile-vision/pull/108
      
      Pull Request resolved: https://github.com/facebookresearch/d2go/pull/373
      
      Asserting that methods replaced by fb_overwritable are also annotated with corresponding decorator.
      
      Reviewed By: wat3rBro
      
      Differential Revision: D39674347
      
      fbshipit-source-id: a4cf007419760aa07d929ab1cf819ba54b11b9da
      fce2a186
  2. 22 Sep, 2022 1 commit
  3. 21 Sep, 2022 1 commit
  4. 15 Sep, 2022 2 commits
  5. 10 Sep, 2022 1 commit
  6. 08 Sep, 2022 1 commit
  7. 31 Aug, 2022 2 commits
  8. 23 Aug, 2022 1 commit
  9. 20 Aug, 2022 1 commit
  10. 18 Aug, 2022 1 commit
  11. 12 Aug, 2022 1 commit
  12. 10 Aug, 2022 1 commit
  13. 09 Aug, 2022 2 commits
  14. 04 Aug, 2022 1 commit
  15. 28 Jul, 2022 1 commit
  16. 27 Jul, 2022 5 commits
  17. 26 Jul, 2022 2 commits
  18. 25 Jul, 2022 1 commit
  19. 22 Jul, 2022 1 commit
  20. 19 Jul, 2022 2 commits
  21. 14 Jul, 2022 4 commits
  22. 13 Jul, 2022 2 commits
  23. 09 Jul, 2022 1 commit
  24. 08 Jul, 2022 3 commits