Skip to content

D
detectron
Switch branch/tag
  1. 24 May, 2018 2 commits
  3. 14 May, 2018 1 commit
  5. 09 May, 2018 1 commit
  7. 08 May, 2018 2 commits
  9. 28 Apr, 2018 1 commit
  11. 27 Apr, 2018 1 commit
  13. 26 Apr, 2018 1 commit
    • Yangqing Jia's avatar
      Use new style caffe2 targets · 8f2f5cf9
      Yangqing Jia authored 
      Summary:
This basically allows Detectron to be built without having to include the many cmake files from Caffe2. Caffe2 now properly exports utility functions and dependent libraries, and so one can use the new style targets "caffe2_library" and "caffe2_gpu_library" directly.

This should also solve problems like #251 after we update the conda version. cc pjh5.
Closes https://github.com/facebookresearch/Detectron/pull/286

Reviewed By: ir413

Differential Revision: D7397696

Pulled By: Yangqing

fbshipit-source-id: 7a47e0addedd4b3c88dd8e2e130afdad04706acc
      8f2f5cf9
  15. 25 Apr, 2018 3 commits
    • Kaiming He's avatar
      typo · 3c4c7f67
      Kaiming He authored 
      Summary: fix a typo in url

Reviewed By: ppwwyyxx

Differential Revision: D7746833

fbshipit-source-id: a0873424ef91625d67f3fbfe44d2b1c5c9c8a4b8
      3c4c7f67
    • Kaiming He's avatar
      add GN documentation · 0dbea626
      Kaiming He authored 
      Summary: Add GN documentation.

Reviewed By: rbgirshick, ppwwyyxx

Differential Revision: D7745878

fbshipit-source-id: 8a49160b1e4026fbcf41082df4a3a8d0f8e90d85
      0dbea626
    • Kaiming He's avatar
      add group norm · c7692eb7
      Kaiming He authored 
      Summary: Add GroupNorm support to master Detectron.

Reviewed By: rbgirshick

Differential Revision: D7611892

fbshipit-source-id: dc4fb84a0e2167b05fd8a94ee0ff1ab1c21369b7
      c7692eb7
  17. 11 Apr, 2018 1 commit
  19. 04 Apr, 2018 1 commit
  21. 03 Apr, 2018 1 commit
  23. 30 Mar, 2018 2 commits
    • Ashwin Bharambe's avatar
      Move `test_net.main()` wrapper inside `test_engine.run_inference` · 22636d44
      Ashwin Bharambe authored 
      Summary:
Another small refactor trying to reduce non-trivial logic existing
inside the `tools` scripts. I considered moving `main` as
`run_inference_and_check_expected_results` but that just sounded uglier.

Reviewed By: rbgirshick

Differential Revision: D7432976

fbshipit-source-id: a31106e11cf0c1d93781fc9a696d2afee553f3d6
      22636d44
    • Ashwin Bharambe's avatar
      Make it possible to run non-EDPM detectron workflows via fblearner · 31738256
      Ashwin Bharambe authored 
      Summary:
This diff adds a `vanilla_detectron` workflow so we can invoke the
non-elastic detectron code (essentially whatever is run by `train_net.par`)
via the standard fblearner toolchain. (FAIR folks typically use `fry` for this
purpose...)

I moved most of the code from `train_net.py` to `lib/utils/train.py` so it can
be re-used.

Note that as of now the `vanilla_detectron` workflow does not run testing.
That's coming.

Reviewed By: rbgirshick

Differential Revision: D7325559

fbshipit-source-id: 41359b47132bc79d1fcd5c5992a3589b391d149e
      31738256
  25. 29 Mar, 2018 1 commit
    • Ross Girshick's avatar
      Add DensePose to README.md · 32acc20c
      Ross Girshick authored 
      Reviewed By: ir413

Differential Revision: D7430607

fbshipit-source-id: 0e8c5f6dc223063505da3620744c8a58b9f5034f
      32acc20c
  27. 28 Mar, 2018 1 commit
  29. 23 Mar, 2018 1 commit
    • shenyunhang's avatar
      Miss a 'None' in return values of create_model() in tools/train_net.py · 7d8da094
      shenyunhang authored 
      Summary:
When 'model_final.pkl' exists, the following error occurs:
```shell
INFO train_net.py: 184: model_final.pkl exists; no need to train!
Traceback (most recent call last):
  File "tools/train_net.py", line 280, in <module>
    main()
  File "tools/train_net.py", line 119, in main
    checkpoints = train_model()
  File "tools/train_net.py", line 128, in train_model
    model, weights_file, start_iter, checkpoints, output_dir = create_model()
ValueError: need more than 4 values to unpack
```
It misses a return value.
Closes https://github.com/facebookresearch/Detectron/pull/309

Reviewed By: ir413

Differential Revision: D7366733

Pulled By: rbgirshick

fbshipit-source-id: c37b3b2e5b2aff38d46ca521a9d79613049255cb
      7d8da094
  31. 22 Mar, 2018 1 commit
  33. 20 Mar, 2018 6 commits
  35. 16 Mar, 2018 1 commit
  37. 15 Mar, 2018 1 commit
  39. 27 Feb, 2018 3 commits
  41. 24 Feb, 2018 1 commit
  43. 23 Feb, 2018 1 commit
  45. 21 Feb, 2018 1 commit
  47. 02 Feb, 2018 3 commits
  49. 01 Feb, 2018 2 commits
    • Ilija Radosavovic's avatar
      Use Caffe2 base docker image from the docker hub · f0d1b0ab
      Ilija Radosavovic authored 
      Reviewed By: rbgirshick

Differential Revision: D6824147

fbshipit-source-id: fe06c4b4ee200003d5d9e4ca62e4afc9741cd929
      f0d1b0ab
    • Ashwin Bharambe's avatar
      Allow for multi-threaded evaluation code · 9df5d8a7
      Ashwin Bharambe authored 
      Summary:
Under certain settings, it is desirable to use multi-threaded
evaluation even though it is inefficient due to Python's GIL. This set of
changes allows for it.

Reviewed By: rbgirshick

Differential Revision: D6827125

fbshipit-source-id: 845647bd09198c35bb6d06c1a453a817d0dcf784
      9df5d8a7