- 11 Apr, 2018 1 commit
-
-
Camille Barneaud authored
Summary: Before this change <code>assert_and_infer_cfg</code> would override the weights passed by the user with CFG ones. It is normal to change it as the user is required to pass weights, otherwise there will be this error : <code>AssertionError: <class 'NoneType'></code>. (verified only in infer_simple.py) Sort of follow-up of eddb1301. Closes https://github.com/facebookresearch/Detectron/pull/331 Reviewed By: ir413 Differential Revision: D7569224 Pulled By: rbgirshick fbshipit-source-id: 00dbaadd2440f39b2b3440b4101a58ed3e68a908
-
- 04 Apr, 2018 1 commit
-
-
Ashwin Bharambe authored
Reviewed By: rbgirshick Differential Revision: D7491769 fbshipit-source-id: 20d8d1f72a773379a3882b697b574b0b0b4f01d3
-
- 03 Apr, 2018 1 commit
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7484464 fbshipit-source-id: f92804fedc3ae040e585e7c0c2eb3e44526eef22
-
- 30 Mar, 2018 2 commits
-
-
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
-
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
-
- 29 Mar, 2018 1 commit
-
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7430607 fbshipit-source-id: 0e8c5f6dc223063505da3620744c8a58b9f5034f
-
- 28 Mar, 2018 1 commit
-
-
Agrim Gupta authored
Reviewed By: rbgirshick Differential Revision: D7015424 fbshipit-source-id: b8e4a998ae55e717f0b7981f15349d93e464b734
-
- 23 Mar, 2018 1 commit
-
-
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
-
- 22 Mar, 2018 1 commit
-
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7364656 fbshipit-source-id: bfd31bc7c95b9606037c2f5546c9edd0e0318272
-
- 20 Mar, 2018 6 commits
-
-
Ross Girshick authored
Reviewed By: ashwinb Differential Revision: D7148434 fbshipit-source-id: 4f5e6386d484b0012ed14dbe1445ee8010d2cc26
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7148432 fbshipit-source-id: e23f767fe0241496b0ee0fb73c247747250eb34e
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7148430 fbshipit-source-id: 71f25716d157daf4082a35dd2138debd9a43c7f1
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7148427 fbshipit-source-id: 25b755c75ddc59cff7a1dc5a5cddb139c44f7cbf
-
Ross Girshick authored
Reviewed By: ir413 Differential Revision: D7148425 fbshipit-source-id: 78c11427b0559248116ca1065b8252355f0034a3
-
Ross Girshick authored
Reviewed By: ashwinb Differential Revision: D7148419 fbshipit-source-id: c8990b7db3c48ea76b665cbda1b9c0985096920c
-
- 16 Mar, 2018 1 commit
-
-
shenyunhang authored
Summary: Fix typos when creating symlinks for PASCAL VOC. Closes https://github.com/facebookresearch/Detectron/pull/275 Reviewed By: rbgirshick Differential Revision: D7274459 Pulled By: ir413 fbshipit-source-id: 8a60516ac199371f67117b29f1ebe3199dabe550
-
- 15 Mar, 2018 1 commit
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7271967 fbshipit-source-id: f42493b08e097bd702b36482b4587a42e5bf3262
-
- 27 Feb, 2018 3 commits
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7086631 fbshipit-source-id: 8d1a756bdd187eb33cde0dac0dc73c5293ca17eb
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7084409 fbshipit-source-id: b1fc559847710e7e4dc35fa8b317c0ba259a4dde
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7082759 fbshipit-source-id: b3257e418944dcfb3c15ff71404c39451d4e225d
-
- 24 Feb, 2018 1 commit
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D7069768 fbshipit-source-id: f254f0073ddc57c43977a8010ca67e89ea1e0c3f
-
- 23 Feb, 2018 1 commit
-
-
Moritz Kampelmuehler authored
Summary: Fixed bug preventing RetinaNet training with num_classes != 81 from converging. Resolves #93 Closes https://github.com/facebookresearch/Detectron/pull/176 Reviewed By: ir413 Differential Revision: D7056134 Pulled By: rbgirshick fbshipit-source-id: d3c62ce98a23a09191dd2720bc7189ee5490635d
-
- 21 Feb, 2018 1 commit
-
-
katotetsuro authored
Summary: This PR fix the issue vis_one_image_opencv raises ValueError. >Since OpenCV 3.2, findContours() no longer modifies the source image but returns a modified image as the first of three return parameters. https://docs.opencv.org/3.3.1/d4/d73/tutorial_py_contours_begin.html and this line also assumes opencv>=3.2 https://github.com/facebookresearch/Detectron/blob/master/lib/utils/vis.py#L326 so, It may be better to set OpenCV version specification to 3.2 or higher in Installation guide. Closes https://github.com/facebookresearch/Detectron/pull/9 Reviewed By: rbgirshick Differential Revision: D7009465 Pulled By: ir413 fbshipit-source-id: 3b2cea6c94da1de93927a6d11724f104c063dca1
-
- 02 Feb, 2018 3 commits
-
-
Ross Girshick authored
Summary: Add link to model zoo training and inference logs Reviewed By: ir413 Differential Revision: D6882050 fbshipit-source-id: 8dabe6ec3b56b47d9f2f00b9d01630eb9911c080
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6875655 fbshipit-source-id: 9c19510ff5c402bef2d947d95d061a5d51e57e9a
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6871605 fbshipit-source-id: 284a9267645cb039c2b20b8ceab68309664b0133
-
- 01 Feb, 2018 4 commits
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6824147 fbshipit-source-id: fe06c4b4ee200003d5d9e4ca62e4afc9741cd929
-
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
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6848494 fbshipit-source-id: 1bc4605443060891872ec1cc7c78216980440003
-
Ashwin Bharambe authored
Summary: Generalizations to enable building forward passes and param update operations separately. Reviewed By: rbgirshick Differential Revision: D6827027 fbshipit-source-id: 9d2ace349b4ebdf8993baa2f2c1529e2c5ce751d
-
- 31 Jan, 2018 6 commits
-
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6845192 fbshipit-source-id: cf172ab7c9fa7137d35839b721b517576994eb35
-
Ashwin Bharambe authored
-
Ashwin Bharambe authored
Summary: Under a distributed setting (multiple nodes), the loss scale may need to account for the number of nodes participating in the algorithm. This method provides a reasonable way for providing this config. Reviewed By: rbgirshick Differential Revision: D6826976 fbshipit-source-id: d224200710b0f3c3245851874c9f4f3ab871710f
-
Ashwin Bharambe authored
Summary: The `AffineChannel` op wrapper did not use the officially sanctioned version of parameter creation, namely using `ModelHelper.create_param()` Presumably this was because of the `share_with` option where you could share parameters. While doing this though, the parameters were never initialized! This probably doesn't matter for the algorithm (those params get overwritten pretty quickly) but it's a bug nevertheless. I decided to kill the `share_with` option since this isn't used anyway and resort to the standard way of creating weights and biases. Reviewed By: rbgirshick Differential Revision: D6826914 fbshipit-source-id: 65628c59b085b9ab160006b003dd40dbefa2f7c1
-
Ashwin Bharambe authored
Summary: This diff starts a series of diffs to refactor the detectron codebase so it can be used in an elastic data parallel context (see https://our.intern.facebook.com/intern/dex/caffe2/elastic-data-parallel-model-for-distributed-training/) without any forks. Specifically, this diff does the following: - Splits out the `TrainingStats` class so it can be reused / composed - Slightly refactor of `initialize_weights_from_file()` - Reduces the verbosity of some logs Hopefully, nothing controversial here :) Reviewed By: rbgirshick Differential Revision: D6826820 fbshipit-source-id: fc15209a0ff50e5d09281e36173198c77aa77a12
-
Ashwin Bharambe authored
-
- 30 Jan, 2018 4 commits
-
-
Kaiming He authored
Summary: Revise print_net to show the full forward model when there are multiple losses (which is always the case). Reviewed By: rbgirshick Differential Revision: D6829753 fbshipit-source-id: 53c1d63d95a78f83a0275b90cad1517315786e7d
-
Ross Girshick authored
Reviewed By: KaimingHe Differential Revision: D6842986 fbshipit-source-id: c8370e2f831239b5489dc723738c6bdf5708a40d
-
Peizhao Zhang authored
Summary: Added a script to convert pkl model to pb. - Supported Faster R-CNN detection model. - Supported converting to CPU and GPU model. - Fused AffineChannel to Conv. - Verified model after conversion. Reviewed By: rbgirshick Differential Revision: D6783633 fbshipit-source-id: 19706d3074a4a784a2161a695d7c534e014ebb3f
-
Ilija Radosavovic authored
Reviewed By: rbgirshick Differential Revision: D6829499 fbshipit-source-id: 66fe40ef1b2c8c560ce769faa27d107c3c7be841
-