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

Support keeping image ratio in the multi-scale training of YOLOX #6732

Merged
merged 3 commits into from
Dec 10, 2021

Conversation

GT9505
Copy link
Collaborator

@GT9505 GT9505 commented Dec 8, 2021

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Support keeping image ratio in the multi-scale training of YOLOX

Modification

Modify the _random_resize() function in the YOLOX detector.

BC-breaking (Optional)

No BC-breaking.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMCls.
  4. The documentation has been modified accordingly, like docstring or example tutorials.

@GT9505 GT9505 changed the base branch from master to dev-v2.19.1 December 9, 2021 05:37
@ZwwWayne
Copy link
Collaborator

ZwwWayne commented Dec 9, 2021

Do we need to run a model to ensure performance? I think originally the image ratio is not kept during training but not it is kept. @hhaAndroid may run an experiment to check the performance

@GT9505
Copy link
Collaborator Author

GT9505 commented Dec 9, 2021

Do we need to run a model to ensure performance? I think originally the image ratio is not kept during training but not it is kept. @hhaAndroid may run an experiment to check the performance

In the orginal YOLOX, the height and width of image are always the same, which means that the aspect_ratio are always 1. Therefore, I think it's unnecessary to rerun an experiments.

@GT9505 GT9505 requested a review from ZwwWayne December 9, 2021 11:27
@ZwwWayne ZwwWayne merged commit 926e457 into open-mmlab:dev-v2.19.1 Dec 10, 2021
ZwwWayne pushed a commit that referenced this pull request Dec 14, 2021
* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos
ZwwWayne pushed a commit that referenced this pull request Dec 15, 2021
* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos
ZwwWayne added a commit that referenced this pull request Dec 24, 2021
* Update README_zh-CN.md (#6652)

* add abstract and sketch to the CONFIGS/algorithm/README.md (#6654)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (#6558)

* Update README.md (#6567)

* [Feature] Support custom persistent_workers (#6435)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (#6574)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (#6501)

* [#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (#6560)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (#6442)

* Refactor YOLOX (#6443)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (#6460)

* [Feature]: Support plot confusion matrix. (#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (#6505)

* Fix type error in 2_new_data_mode (#6469)

* Always map location to cpu when load checkpoint (#6405)

* configs: update groie README (#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (#6396)

* [Enchance] Set a random seed when the user does not set a seed. (#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix #6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (#6584)

* drop support for pytorch 1.3.1. (#6589)

* drop support for pytorch 1.3.1.

* update ci

* update ci

* Skip CI on ignoring paths (#6578)

* [test] Skip CI on ignoring paths

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [skip ci] fix build.yaml

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Refactor]: refactor configs of FP16 models (#6592)

* refactor configs of fp16

* update

* update

* update

* Ignoring paths (#6615)

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* fix FP16 CI (#6616)

* Bump to 2.19.0 (#6633)

* bump to 2.19.0

* resolve comments

* fix typo

* fix

* fix yolox cuda unittest (#6636)

* Support circleci (#6630)

* add ci

* rename

* fix mmtrack unittest

* update mmcv version

* add abstract and sketch to the CONFIGS/algorithm/README.md

* add some ## Introduction

* revert

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>

* [Fix]fix init when densehead contains dcn (#6625)

* fix init when densehead contains dcn

* change to constant init

* fix init of convfchead (#6624)

* polish docs (#6623)

* fix pseudosampler (#6622)

* [Fix]Add an example of combining swin and one-stage models (#6621)

* add an example of swin is used in one-stage model

* fix comments

* add a notice

* add mmhuman3d in readme (#6699)

* [Fix] Fix init weights in Swin and PVT. (#6663)

* [Fix] update metafile (#6717)

* [Fix] fix metafile and config file

* minior fix

* Update configs/seesaw_loss/metafile.yml

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Release YOLOX model (#6698)

* Release YOLOX model

* update

* update

* update

* update

* Add 'get_ann_info' to dataset_wrappers (#6526)

* Add 'get_ann_info' to dataset_wrappers

* fix format

* Delete unimportant notes

* [Enchance] Update FAQ docs (#6587)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (#6558)

* Update README.md (#6567)

* [Feature] Support custom persistent_workers (#6435)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (#6574)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (#6501)

* [#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (#6560)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (#6442)

* Refactor YOLOX (#6443)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (#6460)

* [Feature]: Support plot confusion matrix. (#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (#6505)

* Fix type error in 2_new_data_mode (#6469)

* Always map location to cpu when load checkpoint (#6405)

* configs: update groie README (#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (#6396)

* [Enchance] Set a random seed when the user does not set a seed. (#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix #6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (#6584)

* update faq docs

* update

* update

* update

* fix lint

* update

* update

* update

* update readme

* Rephrase

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* Support keeping image ratio in the multi-scale training of YOLOX (#6732)

* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos

* [Doc]Add doc for detect_anomalous_params (#6697)

* add doc for detect_anomalous_params

* add min verision requirment

* fix version and key

* fix version

* Fix dtype bug in base_dense_head

* Support `bbox_clip_border` for the augmentations of YOLOX (#6730)

* support 'bbox_clip_border' for the augmentations of YOLOX

* update based on 1-st comments

* add comments

* fix typos

* rename remove_ouside_bboxes to find_inside_bboxes

* move comments to docstring

* [Fix] Fix SimOTA with no valid bbox. (#6733)

* [Enhance] support select gpu-ids in testing time

* [Fix] fix link (#6796)

* [Fix] fix lint

* support select gpu-ids in testing time

* minor fix

Co-authored-by: Joson <1250377062@qq.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>
Co-authored-by: ChaimZhu <zcm952742165@gmail.com>
Co-authored-by: Shane Zhao <491498408@qq.com>
Co-authored-by: Tao Gong <gt950513@mail.ustc.edu.cn>
Co-authored-by: Yosuke Shinya <42844407+shinya7y@users.noreply.github.com>
ZwwWayne pushed a commit that referenced this pull request Jul 18, 2022
* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos
ZwwWayne added a commit that referenced this pull request Jul 18, 2022
* Update README_zh-CN.md (#6652)

* add abstract and sketch to the CONFIGS/algorithm/README.md (#6654)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (#6558)

* Update README.md (#6567)

* [Feature] Support custom persistent_workers (#6435)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (#6574)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (#6501)

* [#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (#6560)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (#6442)

* Refactor YOLOX (#6443)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (#6460)

* [Feature]: Support plot confusion matrix. (#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (#6505)

* Fix type error in 2_new_data_mode (#6469)

* Always map location to cpu when load checkpoint (#6405)

* configs: update groie README (#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (#6396)

* [Enchance] Set a random seed when the user does not set a seed. (#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix #6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (#6584)

* drop support for pytorch 1.3.1. (#6589)

* drop support for pytorch 1.3.1.

* update ci

* update ci

* Skip CI on ignoring paths (#6578)

* [test] Skip CI on ignoring paths

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [skip ci] fix build.yaml

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Refactor]: refactor configs of FP16 models (#6592)

* refactor configs of fp16

* update

* update

* update

* Ignoring paths (#6615)

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* fix FP16 CI (#6616)

* Bump to 2.19.0 (#6633)

* bump to 2.19.0

* resolve comments

* fix typo

* fix

* fix yolox cuda unittest (#6636)

* Support circleci (#6630)

* add ci

* rename

* fix mmtrack unittest

* update mmcv version

* add abstract and sketch to the CONFIGS/algorithm/README.md

* add some ## Introduction

* revert

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>

* [Fix]fix init when densehead contains dcn (#6625)

* fix init when densehead contains dcn

* change to constant init

* fix init of convfchead (#6624)

* polish docs (#6623)

* fix pseudosampler (#6622)

* [Fix]Add an example of combining swin and one-stage models (#6621)

* add an example of swin is used in one-stage model

* fix comments

* add a notice

* add mmhuman3d in readme (#6699)

* [Fix] Fix init weights in Swin and PVT. (#6663)

* [Fix] update metafile (#6717)

* [Fix] fix metafile and config file

* minior fix

* Update configs/seesaw_loss/metafile.yml

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Release YOLOX model (#6698)

* Release YOLOX model

* update

* update

* update

* update

* Add 'get_ann_info' to dataset_wrappers (#6526)

* Add 'get_ann_info' to dataset_wrappers

* fix format

* Delete unimportant notes

* [Enchance] Update FAQ docs (#6587)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (#6558)

* Update README.md (#6567)

* [Feature] Support custom persistent_workers (#6435)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (#6574)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (#6501)

* [#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (#6560)

* Fix mosaic repr typo (#6523)

* Include mmflow in readme (#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (#6442)

* Refactor YOLOX (#6443)

* Fix aug test error when the number of prediction bboxes is 0 (#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (#6460)

* [Feature]: Support plot confusion matrix. (#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (#6505)

* Fix type error in 2_new_data_mode (#6469)

* Always map location to cpu when load checkpoint (#6405)

* configs: update groie README (#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (#6396)

* [Enchance] Set a random seed when the user does not set a seed. (#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix #6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (#6584)

* update faq docs

* update

* update

* update

* fix lint

* update

* update

* update

* update readme

* Rephrase

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* Support keeping image ratio in the multi-scale training of YOLOX (#6732)

* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos

* [Doc]Add doc for detect_anomalous_params (#6697)

* add doc for detect_anomalous_params

* add min verision requirment

* fix version and key

* fix version

* Fix dtype bug in base_dense_head

* Support `bbox_clip_border` for the augmentations of YOLOX (#6730)

* support 'bbox_clip_border' for the augmentations of YOLOX

* update based on 1-st comments

* add comments

* fix typos

* rename remove_ouside_bboxes to find_inside_bboxes

* move comments to docstring

* [Fix] Fix SimOTA with no valid bbox. (#6733)

* [Enhance] support select gpu-ids in testing time

* [Fix] fix link (#6796)

* [Fix] fix lint

* support select gpu-ids in testing time

* minor fix

Co-authored-by: Joson <1250377062@qq.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>
Co-authored-by: ChaimZhu <zcm952742165@gmail.com>
Co-authored-by: Shane Zhao <491498408@qq.com>
Co-authored-by: Tao Gong <gt950513@mail.ustc.edu.cn>
Co-authored-by: Yosuke Shinya <42844407+shinya7y@users.noreply.github.com>
ZwwWayne pushed a commit to ZwwWayne/mmdetection that referenced this pull request Jul 19, 2022
…n-mmlab#6732)

* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos
ZwwWayne added a commit to ZwwWayne/mmdetection that referenced this pull request Jul 19, 2022
…-mmlab#6781)

* Update README_zh-CN.md (open-mmlab#6652)

* add abstract and sketch to the CONFIGS/algorithm/README.md (open-mmlab#6654)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (open-mmlab#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (open-mmlab#6558)

* Update README.md (open-mmlab#6567)

* [Feature] Support custom persistent_workers (open-mmlab#6435)

* Fix aug test error when the number of prediction bboxes is 0 (open-mmlab#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (open-mmlab#6574)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (open-mmlab#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (open-mmlab#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (open-mmlab#6501)

* [open-mmlab#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (open-mmlab#6560)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (open-mmlab#6442)

* Refactor YOLOX (open-mmlab#6443)

* Fix aug test error when the number of prediction bboxes is 0 (open-mmlab#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (open-mmlab#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (open-mmlab#6460)

* [Feature]: Support plot confusion matrix. (open-mmlab#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (open-mmlab#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (open-mmlab#6505)

* Fix type error in 2_new_data_mode (open-mmlab#6469)

* Always map location to cpu when load checkpoint (open-mmlab#6405)

* configs: update groie README (open-mmlab#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (open-mmlab#6396)

* [Enchance] Set a random seed when the user does not set a seed. (open-mmlab#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (open-mmlab#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix open-mmlab#6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (open-mmlab#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (open-mmlab#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (open-mmlab#6584)

* drop support for pytorch 1.3.1. (open-mmlab#6589)

* drop support for pytorch 1.3.1.

* update ci

* update ci

* Skip CI on ignoring paths (open-mmlab#6578)

* [test] Skip CI on ignoring paths

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [skip ci] fix build.yaml

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* split lint in workflows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Refactor]: refactor configs of FP16 models (open-mmlab#6592)

* refactor configs of fp16

* update

* update

* update

* Ignoring paths (open-mmlab#6615)

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* fix FP16 CI (open-mmlab#6616)

* Bump to 2.19.0 (open-mmlab#6633)

* bump to 2.19.0

* resolve comments

* fix typo

* fix

* fix yolox cuda unittest (open-mmlab#6636)

* Support circleci (open-mmlab#6630)

* add ci

* rename

* fix mmtrack unittest

* update mmcv version

* add abstract and sketch to the CONFIGS/algorithm/README.md

* add some ## Introduction

* revert

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>

* [Fix]fix init when densehead contains dcn (open-mmlab#6625)

* fix init when densehead contains dcn

* change to constant init

* fix init of convfchead (open-mmlab#6624)

* polish docs (open-mmlab#6623)

* fix pseudosampler (open-mmlab#6622)

* [Fix]Add an example of combining swin and one-stage models (open-mmlab#6621)

* add an example of swin is used in one-stage model

* fix comments

* add a notice

* add mmhuman3d in readme (open-mmlab#6699)

* [Fix] Fix init weights in Swin and PVT. (open-mmlab#6663)

* [Fix] update metafile (open-mmlab#6717)

* [Fix] fix metafile and config file

* minior fix

* Update configs/seesaw_loss/metafile.yml

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Release YOLOX model (open-mmlab#6698)

* Release YOLOX model

* update

* update

* update

* update

* Add 'get_ann_info' to dataset_wrappers (open-mmlab#6526)

* Add 'get_ann_info' to dataset_wrappers

* fix format

* Delete unimportant notes

* [Enchance] Update FAQ docs (open-mmlab#6587)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* [Enhance] Support file_client in Datasets and evaluating panoptic results on Ceph (open-mmlab#6489)

* first version

* Replace with our api

* Add copyright

* Move the runtime error to multi_core interface

* Add docstring

* Fix comments

* Add comments

* Add unit test for pq_compute_single_core

* Fix MMDetection model to ONNX command (open-mmlab#6558)

* Update README.md (open-mmlab#6567)

* [Feature] Support custom persistent_workers (open-mmlab#6435)

* Fix aug test error when the number of prediction bboxes is 0 (open-mmlab#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* fix comment

* fix docstr

* remove pin_memory

* Fix SSD512 config error (open-mmlab#6574)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* Fix ssd512 config error

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* Catch symlink failure on Windows (open-mmlab#6482)

* Catch symlink failure on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Set copy mode on Windows

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix lint

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* Fix logic error

Signed-off-by: del-zhenwu <dele.zhenwu@gmail.com>

* [Feature] Support Label Assignment Distillation (LAD) (open-mmlab#6342)

* add LAD

* inherit LAD from KnowledgeDistillationSingleStageDetector

* add configs/lad/lad_r101_paa_r50_fpn_coco_1x.py

* update LAD readme

* update configs/lad/README.md

* try not to use abbreviations for variable names

* add unittest for lad_head

* update test_lad_head

* remove main in tests/test_models/test_dense_heads/test_lad_head.py

* [Fix] Avoid infinite GPU waiting in dist training (open-mmlab#6501)

* [open-mmlab#6495] fix infinite GPU waiting in dist training

* print log_vars keys in assertion msg

* linting issue

* Support to collect the best models (open-mmlab#6560)

* Fix mosaic repr typo (open-mmlab#6523)

* Include mmflow in readme (open-mmlab#6545)

* Include mmflow in readme

* Include mmflow in README_zh-CN

* Add mmflow url into the document menu in docs/conf.py and docs_zh-CN/conf.py.

* Make OHEM work with seesaw loss (open-mmlab#6514)

* update

* support gather best model

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>

* [Enhance]: Optimize augmentation pipeline to speed up training. (open-mmlab#6442)

* Refactor YOLOX (open-mmlab#6443)

* Fix aug test error when the number of prediction bboxes is 0 (open-mmlab#6398)

* Fix aug test error when the number of prediction bboxes is 0

* test

* test

* fix lint

* Support custom pin_memory and persistent_workers

* [Docs] Chinese version of robustness_benchmarking.md (open-mmlab#6375)

* Chinese version of robustness_benchmarking.md

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update docs_zh-CN/robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

* Update robustness_benchmarking.md

Co-authored-by: RangiLyu <lyuchqi@gmail.com>

* update yolox_s

* update yolox_s

* support dynamic eval interval

* fix some error

* support ceph

* fix none error

* fix batch error

* replace resize

* fix comment

* fix docstr

* Update the link of checkpoints (open-mmlab#6460)

* [Feature]: Support plot confusion matrix. (open-mmlab#6344)

* remove pin_memory

* update

* fix unittest

* update cfg

* fix error

* add unittest

* [Fix] Fix SpatialReductionAttention in PVT. (open-mmlab#6488)

* [Fix] Fix SpatialReductionAttention in PVT

* Add warning

* Save coco summarize print information to logger (open-mmlab#6505)

* Fix type error in 2_new_data_mode (open-mmlab#6469)

* Always map location to cpu when load checkpoint (open-mmlab#6405)

* configs: update groie README (open-mmlab#6401)

Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it>

* [Fix] fix config path in docs (open-mmlab#6396)

* [Enchance] Set a random seed when the user does not set a seed. (open-mmlab#6457)

* fix random seed bug

* add comment

* enchance random seed

* rename

Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>

* [BugFixed] fix wrong trunc_normal_init use (open-mmlab#6432)

* fix wrong trunc_normal_init use

* fix wrong trunc_normal_init use

* fix open-mmlab#6446

Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* bump version to v2.18.1 (open-mmlab#6510)

* bump version to v2.18.1

* Update changelog.md

* add some comment

* fix some comment

* update readme

* fix lint

* add reduce mean

* update

* update readme

* update params

Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>

* [Refactor] Remove some code in `mmdet/apis/train.py` (open-mmlab#6576)

* remove some code about custom hooks in apis/train.py

* files were modified by yapf

* Fix lad repeatedly output warning message (open-mmlab#6584)

* update faq docs

* update

* update

* update

* fix lint

* update

* update

* update

* update readme

* Rephrase

Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: BigDong <yudongwang@tju.edu.cn>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>

* Support keeping image ratio in the multi-scale training of YOLOX (open-mmlab#6732)

* Support keeping ratio in the multi-scale training of YOLOX

* fix typos

* fix typos

* [Doc]Add doc for detect_anomalous_params (open-mmlab#6697)

* add doc for detect_anomalous_params

* add min verision requirment

* fix version and key

* fix version

* Fix dtype bug in base_dense_head

* Support `bbox_clip_border` for the augmentations of YOLOX (open-mmlab#6730)

* support 'bbox_clip_border' for the augmentations of YOLOX

* update based on 1-st comments

* add comments

* fix typos

* rename remove_ouside_bboxes to find_inside_bboxes

* move comments to docstring

* [Fix] Fix SimOTA with no valid bbox. (open-mmlab#6733)

* [Enhance] support select gpu-ids in testing time

* [Fix] fix link (open-mmlab#6796)

* [Fix] fix lint

* support select gpu-ids in testing time

* minor fix

Co-authored-by: Joson <1250377062@qq.com>
Co-authored-by: Czm369 <40661020+Czm369@users.noreply.github.com>
Co-authored-by: Kyungmin Lee <30465912+lkm2835@users.noreply.github.com>
Co-authored-by: ohwi <supebulous@gmail.com>
Co-authored-by: Guangchen Lin <347630870@qq.com>
Co-authored-by: Rishit Dagli <rishit.dagli@gmail.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: del-zhenwu <dele.zhenwu@gmail.com>
Co-authored-by: Thuy Ng <thuypn9a4@gmail.com>
Co-authored-by: Han Zhang <623606860@qq.com>
Co-authored-by: Cedric Luo <luochunhua1996@outlook.com>
Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com>
Co-authored-by: Uno Wu <st9007a@gmail.com>
Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it>
Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn>
Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>
Co-authored-by: ChaimZhu <zcm952742165@gmail.com>
Co-authored-by: Shane Zhao <491498408@qq.com>
Co-authored-by: Tao Gong <gt950513@mail.ustc.edu.cn>
Co-authored-by: Yosuke Shinya <42844407+shinya7y@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants