diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 086f417804f..fcc3af1fce3 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -13,17 +13,19 @@ All kinds of contributions are welcome, including but not limited to the followi 4. create a PR Note + - If you plan to add some new features that involve large changes, it is encouraged to open an issue for discussion first. -- If you are the author of some papers and would like to include your method to mmdetection, -please let us know (open an issue or contact the maintainers). We will much appreciate your contribution. +- If you are the author of some papers and would like to include your method to mmdetection, please let us know (open an issue or contact the maintainers). We will much appreciate your contribution. - For new features and new modules, unit tests are required to improve the code's robustness. ## Code style ### Python + We adopt [PEP8](https://www.python.org/dev/peps/pep-0008/) as the preferred code style. We use the following tools for linting and formatting: + - [flake8](http://flake8.pycqa.org/en/latest/): linter - [yapf](https://github.com/google/yapf): formatter - [isort](https://github.com/timothycrosley/isort): sort imports @@ -36,19 +38,33 @@ The config for a pre-commit hook is stored in [.pre-commit-config](../.pre-commi After you clone the repository, you will need to install initialize pre-commit hook. -``` +```shell pip install -U pre-commit ``` From the repository folder -``` + +```shell pre-commit install ``` -After this on every commit check code linters and formatter will be enforced. +If you are facing issue when installing markdown lint, you may install ruby for markdown lint by following + +```shell +# install rvm +curl -L https://get.rvm.io | bash -s -- --autolibs=read-fail +# set up environment +echo 'source $HOME/.bash_profile' >> ~/.bashrc +source ~/.profile +rvm autolibs disable +# install ruby +rvm install 2.7.1 +``` +After this on every commit check code linters and formatter will be enforced. >Before you create a PR, make sure that your code lints and is formatted by yapf. ### C++ and CUDA + We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html). diff --git a/.github/ISSUE_TEMPLATE/error-report.md b/.github/ISSUE_TEMPLATE/error-report.md index acdfd352148..ec28669514c 100644 --- a/.github/ISSUE_TEMPLATE/error-report.md +++ b/.github/ISSUE_TEMPLATE/error-report.md @@ -10,6 +10,7 @@ assignees: '' Thanks for your error report and we appreciate it a lot. **Checklist** + 1. I have searched related issues but cannot get the expected help. 2. The bug has not been fixed in the latest version. @@ -17,10 +18,13 @@ Thanks for your error report and we appreciate it a lot. A clear and concise description of what the bug is. **Reproduction** + 1. What command or script did you run? -``` + +```none A placeholder for the command. ``` + 2. Did you make any modifications on the code or config? Did you understand what you have modified? 3. What dataset did you use? @@ -33,7 +37,8 @@ A placeholder for the command. **Error traceback** If applicable, paste the error trackback here. -``` + +```none A placeholder for trackback. ``` diff --git a/.github/ISSUE_TEMPLATE/reimplementation_questions.md b/.github/ISSUE_TEMPLATE/reimplementation_questions.md index 58ffdeb3f0f..6b358387701 100644 --- a/.github/ISSUE_TEMPLATE/reimplementation_questions.md +++ b/.github/ISSUE_TEMPLATE/reimplementation_questions.md @@ -10,17 +10,20 @@ assignees: '' **Notice** There are several common situations in the reimplementation issues as below + 1. Reimplement a model in the model zoo using the provided configs 2. Reimplement a model in the model zoo on other dataset (e.g., custom datasets) 3. Reimplement a custom model but all the components are implemented in MMDetection 4. Reimplement a custom model with new modules implemented by yourself There are several things to do for different cases as below. + - For case 1 & 3, please follow the steps in the following sections thus we could help to quick identify the issue. - For case 2 & 4, please understand that we are not able to do much help here because we usually do not know the full code and the users should be responsible to the code they write. - One suggestion for case 2 & 4 is that the users should first check whether the bug lies in the self-implemented code or the original code. For example, users can first make sure that the same model runs well on supported datasets. If you still need help, please describe what you have done and what you obtain in the issue, and follow the steps in the following sections and try as clear as possible so that we can better help you. **Checklist** + 1. I have searched related issues but cannot get the expected help. 2. The issue has not been fixed in the latest version. @@ -29,14 +32,19 @@ There are several things to do for different cases as below. A clear and concise description of what the problem you meet and what have you done. **Reproduction** + 1. What command or script did you run? -``` + +```none A placeholder for the command. ``` + 2. What config dir you run? -``` + +```none A placeholder for the config. ``` + 3. Did you make any modifications on the code or config? Did you understand what you have modified? 4. What dataset did you use? @@ -44,13 +52,14 @@ A placeholder for the config. 1. Please run `python mmdet/utils/collect_env.py` to collect necessary environment information and paste it here. 2. You may add addition that may be helpful for locating the problem, such as - - How you installed PyTorch [e.g., pip, conda, source] - - Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.) + 1. How you installed PyTorch [e.g., pip, conda, source] + 2. Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.) **Results** If applicable, paste the related results here, e.g., what you expect and what you get. -``` + +```none A placeholder for results comparison ``` diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 9e6d30895b0..35566b35337 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -28,6 +28,11 @@ repos: args: ["--remove"] - id: mixed-line-ending args: ["--fix=lf"] + - repo: https://github.com/jumanjihouse/pre-commit-hooks + rev: 2.1.4 + hooks: + - id: markdownlint + args: ["-r", "~MD002,~MD013,~MD024,~MD029,~MD033,~MD034,~MD036"] - repo: https://github.com/myint/docformatter rev: v1.3.1 hooks: diff --git a/README.md b/README.md index 1a01c4e2c16..7c698d77868 100644 --- a/README.md +++ b/README.md @@ -51,6 +51,7 @@ A comparison between v1.x and v2.0 codebases can be found in [compatibility.md]( Results and models are available in the [model zoo](docs/model_zoo.md). Supported backbones: + - [x] ResNet - [x] ResNeXt - [x] VGG @@ -60,6 +61,7 @@ Supported backbones: - [x] ResNeSt Supported methods: + - [x] [RPN](configs/rpn) - [x] [Fast R-CNN](configs/fast_rcnn) - [x] [Faster R-CNN](configs/faster_rcnn) diff --git a/configs/atss/README.md b/configs/atss/README.md index b34307f436d..99f571652c5 100644 --- a/configs/atss/README.md +++ b/configs/atss/README.md @@ -1,9 +1,8 @@ # Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection - ## Introduction -``` +```latex @article{zhang2019bridging, title = {Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection}, author = {Zhang, Shifeng and Chi, Cheng and Yao, Yongqiang and Lei, Zhen and Li, Stan Z.}, @@ -12,7 +11,6 @@ } ``` - ## Results and Models | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | diff --git a/configs/cascade_rcnn/README.md b/configs/cascade_rcnn/README.md index 3ad625a8e4a..74c99066114 100644 --- a/configs/cascade_rcnn/README.md +++ b/configs/cascade_rcnn/README.md @@ -1,7 +1,8 @@ # Cascade R-CNN: High Quality Object Detection and Instance Segmentation ## Introduction -``` + +```latex @article{Cai_2019, title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation}, ISSN={1939-3539}, diff --git a/configs/centripetalnet/README.md b/configs/centripetalnet/README.md index 5c83422291a..ca502e5d7ab 100644 --- a/configs/centripetalnet/README.md +++ b/configs/centripetalnet/README.md @@ -1,7 +1,8 @@ # CentripetalNet ## Introduction -``` + +```latex @InProceedings{Dong_2020_CVPR, author = {Dong, Zhiwei and Li, Guoxuan and Liao, Yue and Wang, Fei and Ren, Pengju and Qian, Chen}, title = {CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection}, @@ -18,5 +19,6 @@ year = {2020} | HourglassNet-104 | [16 x 6](./centripetalnet_hourglass104_mstest_16x6_210e_coco.py) | 190/210 | 16.7 | 3.7 | 44.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804-3ccc61e5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804.log.json) | Note: + - TTA setting is single-scale and `flip=True`. - The model we released is the best checkpoint rather than the latest checkpoint (box AP 44.8 vs 44.6 in our experiment). diff --git a/configs/cityscapes/README.md b/configs/cityscapes/README.md index 80ce589c562..146ec0d07c1 100644 --- a/configs/cityscapes/README.md +++ b/configs/cityscapes/README.md @@ -9,7 +9,6 @@ - A conversion [script](../../tools/convert_datasets/cityscapes.py) is provided to convert Cityscapes into COCO format. Please refer to [install.md](../../docs/install.md#prepare-datasets) for details. - `CityscapesDataset` implemented three evaluation methods. `bbox` and `segm` are standard COCO bbox/mask AP. `cityscapes` is the cityscapes dataset official evaluation, which may be slightly higher than COCO. - ### Faster R-CNN | Backbone | Style | Lr schd | Scale | Mem (GB) | Inf time (fps) | box AP | Config | Download | diff --git a/configs/cornernet/README.md b/configs/cornernet/README.md index 457200c8088..65a7eda2ff0 100644 --- a/configs/cornernet/README.md +++ b/configs/cornernet/README.md @@ -1,7 +1,8 @@ # CornerNet ## Introduction -``` + +```latex @inproceedings{law2018cornernet, title={Cornernet: Detecting objects as paired keypoints}, author={Law, Hei and Deng, Jia}, @@ -21,9 +22,10 @@ | HourglassNet-104 | [32 x 3](./cornernet_hourglass104_mstest_32x3_210e_coco.py) | 180/210 | 9.5 | 3.9 | 40.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/cornernet/cornernet_hourglass104_mstest_32x3_210e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/cornernet/cornernet_hourglass104_mstest_32x3_210e_coco/cornernet_hourglass104_mstest_32x3_210e_coco_20200819_203110-1efaea91.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/cornernet/cornernet_hourglass104_mstest_32x3_210e_coco/cornernet_hourglass104_mstest_32x3_210e_coco_20200819_203110.log.json) | Note: + - TTA setting is single-scale and `flip=True`. - Experiments with `images_per_gpu=6` are conducted on Tesla V100-SXM2-32GB, `images_per_gpu=3` are conducted on GeForce GTX 1080 Ti. - Here are the descriptions of each experiment setting: - - 10 x 5: 10 GPUs with 5 images per gpu. This is the same setting as that reported in the original paper. - - 8 x 6: 8 GPUs with 6 images per gpu. The total batchsize is similar to paper and only need 1 node to train. - - 32 x 3: 32 GPUs with 3 images per gpu. The default setting for 1080TI and need 4 nodes to train. + - 10 x 5: 10 GPUs with 5 images per gpu. This is the same setting as that reported in the original paper. + - 8 x 6: 8 GPUs with 6 images per gpu. The total batchsize is similar to paper and only need 1 node to train. + - 32 x 3: 32 GPUs with 3 images per gpu. The default setting for 1080TI and need 4 nodes to train. diff --git a/configs/dcn/README.md b/configs/dcn/README.md index 94bec674ed0..9c42f94d791 100644 --- a/configs/dcn/README.md +++ b/configs/dcn/README.md @@ -1,8 +1,8 @@ # Deformable Convolutional Networks -# Introduction +## Introduction -``` +```none @inproceedings{dai2017deformable, title={Deformable Convolutional Networks}, author={Dai, Jifeng and Qi, Haozhi and Xiong, Yuwen and Li, Yi and Zhang, Guodong and Hu, Han and Wei, Yichen}, diff --git a/configs/deepfashion/README.md b/configs/deepfashion/README.md index c087575b73a..fa31cca8eef 100644 --- a/configs/deepfashion/README.md +++ b/configs/deepfashion/README.md @@ -1,6 +1,6 @@ # DeepFashion -MMFashion(https://github.com/open-mmlab/mmfashion) develops "fashion parsing and segmentation" module +[MMFashion](https://github.com/open-mmlab/mmfashion) develops "fashion parsing and segmentation" module based on the dataset [DeepFashion-Inshop](https://drive.google.com/drive/folders/0B7EVK8r0v71pVDZFQXRsMDZCX1E?usp=sharing). Its annotation follows COCO style. @@ -38,6 +38,7 @@ After that you can train the Mask RCNN r50 on DeepFashion-In-shop dataset by lau or creating your own config file. ## Model Zoo + | Backbone | Model type | Dataset | bbox detection Average Precision | segmentation Average Precision | Config | Download (Google) | | :---------: | :----------: | :-----------------: | :--------------------------------: | :----------------------------: | :---------:| :-------------------------: | | ResNet50 | Mask RCNN | DeepFashion-In-shop | 0.599 | 0.584 |[config](https://github.com/open-mmlab/mmdetection/blob/master/configs/deepfashion/mask_rcnn_r50_fpn_15e_deepfashion.py)| [model](https://drive.google.com/open?id=1q6zF7J6Gb-FFgM87oIORIt6uBozaXp5r) | [log](https://drive.google.com/file/d/1qTK4Dr4FFLa9fkdI6UVko408gkrfTRLP/view?usp=sharing) | diff --git a/configs/double_heads/README.md b/configs/double_heads/README.md index 049dad5dca8..6c031d0b856 100644 --- a/configs/double_heads/README.md +++ b/configs/double_heads/README.md @@ -1,7 +1,8 @@ # Rethinking Classification and Localization for Object Detection ## Introduction -``` + +```latex @article{wu2019rethinking, title={Rethinking Classification and Localization for Object Detection}, author={Yue Wu and Yinpeng Chen and Lu Yuan and Zicheng Liu and Lijuan Wang and Hongzhi Li and Yun Fu}, diff --git a/configs/empirical_attention/README.md b/configs/empirical_attention/README.md index 1e737ea0053..ed151178503 100644 --- a/configs/empirical_attention/README.md +++ b/configs/empirical_attention/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @article{zhu2019empirical, title={An Empirical Study of Spatial Attention Mechanisms in Deep Networks}, author={Zhu, Xizhou and Cheng, Dazhi and Zhang, Zheng and Lin, Stephen and Dai, Jifeng}, @@ -11,7 +11,6 @@ } ``` - ## Results and Models | Backbone | Attention Component | DCN | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | diff --git a/configs/fast_rcnn/README.md b/configs/fast_rcnn/README.md index b01c4b5956d..1c9da5079d1 100644 --- a/configs/fast_rcnn/README.md +++ b/configs/fast_rcnn/README.md @@ -1,7 +1,8 @@ # Fast R-CNN ## Introduction -``` + +```latex @inproceedings{girshick2015fast, title={Fast r-cnn}, author={Girshick, Ross}, diff --git a/configs/faster_rcnn/README.md b/configs/faster_rcnn/README.md index a331ccd3bf4..5152317b380 100644 --- a/configs/faster_rcnn/README.md +++ b/configs/faster_rcnn/README.md @@ -1,7 +1,8 @@ # Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks ## Introduction -``` + +```latex @article{Ren_2017, title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, @@ -29,6 +30,7 @@ | X-101-64x4d-FPN | pytorch | 2x | - | - | 41.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco/faster_rcnn_x101_64x4d_fpn_2x_coco_20200512_161033-5961fa95.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_2x_coco/faster_rcnn_x101_64x4d_fpn_2x_coco_20200512_161033.log.json) | ## Different regression loss + We trained with R-50-FPN pytorch style backbone for 1x schedule. | Backbone | Loss type | Mem (GB) | Inf time (fps) | box AP | Config | Download | @@ -39,6 +41,7 @@ We trained with R-50-FPN pytorch style backbone for 1x schedule. | R-50-FPN | BoundedIoULoss | | | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco-98ad993b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_bounded_iou_1x_coco_20200505_160738.log.json) | ## Pre-trained Models + We also train some models with longer schedules and multi-scale training. The users could finetune them for downstream tasks. | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | diff --git a/configs/fcos/README.md b/configs/fcos/README.md index d7c0d419736..84b3fbfaaf5 100644 --- a/configs/fcos/README.md +++ b/configs/fcos/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @article{tian2019fcos, title={FCOS: Fully Convolutional One-Stage Object Detection}, author={Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong}, @@ -23,7 +23,6 @@ | R-101 | caffe | Y | N | N | N | 1x | 10.2 | 17.3 | 39.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_r101_caffe_fpn_gn-head_4x4_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r101_caffe_fpn_gn-head_4x4_1x_coco/fcos_r101_caffe_fpn_gn_1x_4gpu_20200218-13e2cc55.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r101_caffe_fpn_gn-head_4x4_1x_coco/20200130_004231.log.json) | | R-101 | caffe | Y | N | N | N | 2x | - | - | 39.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_r101_caffe_fpn_gn-head_4x4_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r101_caffe_fpn_gn-head_4x4_2x_coco/fcos_r101_caffe_fpn_gn_2x_4gpu_20200218-d2261033.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r101_caffe_fpn_gn-head_4x4_2x_coco/20200130_004231.log.json) | - | Backbone | Style | GN | MS train | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | |:---------:|:-------:|:-------:|:--------:|:-------:|:--------:|:--------------:|:------:|:------:|:--------:| | R-50 | caffe | Y | Y | 2x | 6.5 | 22.9 | 38.7 | | | @@ -31,6 +30,7 @@ | X-101 | pytorch | Y | Y | 2x | 10.0 | 9.3 | 42.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_4x2_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_4x2_2x_coco/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_4x2_2x_coco_20200229-11f8c079.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_4x2_2x_coco/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_4x2_2x_coco_20200229_222104.log.json) | **Notes:** + - To be consistent with the author's implementation, we use 4 GPUs with 4 images/GPU for R-50 and R-101 models, and 8 GPUs with 2 image/GPU for X-101 models. - The X-101 backbone is X-101-64x4d. - Tricks means setting `norm_on_bbox`, `centerness_on_reg`, `center_sampling` as `True`. diff --git a/configs/foveabox/README.md b/configs/foveabox/README.md index 4ea751e930b..7b69178d4c8 100644 --- a/configs/foveabox/README.md +++ b/configs/foveabox/README.md @@ -4,6 +4,7 @@ FoveaBox is an accurate, flexible and completely anchor-free object detection sy Different from previous anchor-based methods, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. ## Main Results + ### Results on R50/101-FPN | Backbone | Style | align | ms-train| Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | @@ -25,8 +26,10 @@ Different from previous anchor-based methods, FoveaBox directly learns the objec Any pull requests or issues are welcome. ## Citations + Please consider citing our paper in your publications if the project helps your research. BibTeX reference is as follows. -``` + +```latex @article{kong2019foveabox, title={FoveaBox: Beyond Anchor-based Object Detector}, author={Kong, Tao and Sun, Fuchun and Liu, Huaping and Jiang, Yuning and Shi, Jianbo}, diff --git a/configs/fp16/README.md b/configs/fp16/README.md index e8ec8721084..bca4fb9cda3 100644 --- a/configs/fp16/README.md +++ b/configs/fp16/README.md @@ -1,7 +1,8 @@ # Mixed Precision Training ## Introduction -``` + +```latex @article{micikevicius2017mixed, title={Mixed precision training}, author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others}, diff --git a/configs/free_anchor/README.md b/configs/free_anchor/README.md index 85a675e92c3..0cbb7afeaad 100644 --- a/configs/free_anchor/README.md +++ b/configs/free_anchor/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{zhang2019freeanchor, title = {{FreeAnchor}: Learning to Match Anchors for Visual Object Detection}, author = {Zhang, Xiaosong and Wan, Fang and Liu, Chang and Ji, Rongrong and Ye, Qixiang}, @@ -20,5 +20,6 @@ | X-101-32x4d | pytorch | 1x | 8.1 | 11.1 | 41.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/free_anchor/retinanet_free_anchor_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/free_anchor/retinanet_free_anchor_x101_32x4d_fpn_1x_coco/retinanet_free_anchor_x101_32x4d_fpn_1x_coco_20200130-d4846968.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/free_anchor/retinanet_free_anchor_x101_32x4d_fpn_1x_coco/retinanet_free_anchor_x101_32x4d_fpn_1x_coco_20200130_095627.log.json) | **Notes:** + - We use 8 GPUs with 2 images/GPU. - For more settings and models, please refer to the [official repo](https://github.com/zhangxiaosong18/FreeAnchor). diff --git a/configs/fsaf/README.md b/configs/fsaf/README.md index 8039bfb36ed..a07fe648f1c 100644 --- a/configs/fsaf/README.md +++ b/configs/fsaf/README.md @@ -9,6 +9,7 @@ In the original paper, feature maps within the central 0.2-0.5 area of a gt box it is empirically found that a hard threshold (0.2-0.2) gives a further gain on the performance. (see the table below) ## Main Results + ### Results on R50/R101/X101-FPN | Backbone | ignore range | ms-train| Lr schd |Train Mem (GB)| Train time (s/iter) | Inf time (fps) | box AP | Config | Download | @@ -19,16 +20,19 @@ it is empirically found that a hard threshold (0.2-0.2) gives a further gain on | X-101 | 0.2-0.2 | N | 1x | 9.38 | 1.23 | 5.6 | 42.4 (41.0) | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fsaf/fsaf_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_x101_64x4d_fpn_1x_coco/fsaf_x101_64x4d_fpn_1x_coco-e3f6e6fd.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_x101_64x4d_fpn_1x_coco/fsaf_x101_64x4d_fpn_1x_coco_20200428_160424.log.json)| **Notes:** - - *1x means the model is trained for 12 epochs.* - - *AP values in the brackets represent those reported in the original paper.* - - *All results are obtained with a single model and single-scale test.* - - *X-101 backbone represents ResNext-101-64x4d.* - - *All pretrained backbones use pytorch style.* - - *All models are trained on 8 Titan-XP gpus and tested on a single gpu.* + +- *1x means the model is trained for 12 epochs.* +- *AP values in the brackets represent those reported in the original paper.* +- *All results are obtained with a single model and single-scale test.* +- *X-101 backbone represents ResNext-101-64x4d.* +- *All pretrained backbones use pytorch style.* +- *All models are trained on 8 Titan-XP gpus and tested on a single gpu.* ## Citations + BibTeX reference is as follows. -``` + +```latex @inproceedings{zhu2019feature, title={Feature Selective Anchor-Free Module for Single-Shot Object Detection}, author={Zhu, Chenchen and He, Yihui and Savvides, Marios}, diff --git a/configs/gcnet/README.md b/configs/gcnet/README.md index 7c9e29c1ba9..0fe0fc101d1 100644 --- a/configs/gcnet/README.md +++ b/configs/gcnet/README.md @@ -11,7 +11,7 @@ We provide config files to reproduce the results in the paper for ## Citing GCNet -``` +```latex @article{cao2019GCNet, title={GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond}, author={Cao, Yue and Xu, Jiarui and Lin, Stephen and Wei, Fangyun and Hu, Han}, @@ -21,6 +21,7 @@ We provide config files to reproduce the results in the paper for ``` ## Results and models + The results on COCO 2017val are shown in the below table. | Backbone | Model | Context | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | diff --git a/configs/gfl/README.md b/configs/gfl/README.md index b379f6850ed..7ca72cc574d 100644 --- a/configs/gfl/README.md +++ b/configs/gfl/README.md @@ -1,11 +1,10 @@ # Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection - ## Introduction We provide config files to reproduce the object detection results in the paper [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://arxiv.org/abs/2006.04388) -``` +```latex @article{li2020generalized, title={Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection}, author={Li, Xiang and Wang, Wenhai and Wu, Lijun and Chen, Shuo and Hu, Xiaolin and Li, Jun and Tang, Jinhui and Yang, Jian}, @@ -14,7 +13,6 @@ We provide config files to reproduce the object detection results in the paper [ } ``` - ## Results and Models | Backbone | Style | Lr schd | Multi-scale Training| Inf time (fps) | box AP | Config | Download | diff --git a/configs/gn/README.md b/configs/gn/README.md index 205892afcd7..d6db55ea05b 100644 --- a/configs/gn/README.md +++ b/configs/gn/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{wu2018group, title={Group Normalization}, author={Wu, Yuxin and He, Kaiming}, @@ -23,6 +23,7 @@ | R-50-FPN (c) | Mask R-CNN | 3x | 7.1 | - | 40.1 | 36.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/gn/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/gn/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco_20200225-542aefbc.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/gn/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco/mask_rcnn_r50_fpn_gn-all_contrib_3x_coco_20200225_235135.log.json) | **Notes:** + - (d) means pretrained model converted from Detectron, and (c) means the contributed model pretrained by [@thangvubk](https://github.com/thangvubk). - The `3x` schedule is epoch [28, 34, 36]. - **Memory, Train/Inf time is outdated.** diff --git a/configs/grid_rcnn/README.md b/configs/grid_rcnn/README.md index d6f4966511a..96b598f881b 100644 --- a/configs/grid_rcnn/README.md +++ b/configs/grid_rcnn/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{lu2019grid, title={Grid r-cnn}, author={Lu, Xin and Li, Buyu and Yue, Yuxin and Li, Quanquan and Yan, Junjie}, @@ -28,5 +28,6 @@ | X-101-64x4d | 2x | 11.3 | 7.7 | 43.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/grid_rcnn/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/grid_rcnn/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco_20200204-ec76a754.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/grid_rcnn/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco/grid_rcnn_x101_64x4d_fpn_gn-head_2x_coco_20200204_080641.log.json) | **Notes:** + - All models are trained with 8 GPUs instead of 32 GPUs in the original paper. - The warming up lasts for 1 epoch and `2x` here indicates 25 epochs. diff --git a/configs/groie/README.md b/configs/groie/README.md index 9ccb9128599..05385618c16 100644 --- a/configs/groie/README.md +++ b/configs/groie/README.md @@ -42,12 +42,11 @@ the trained models. | R-101-FPN | GC-Net | 1x | 42.2 | 37.8 | [config](../configs/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco_20200206-8407a3f0.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco_20200206_142508.log.json) | | R-101-FPN | + GRoIE | 1x | | | [config](./mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py)| [model](http://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200607_224507-8daae01c.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200607_224507.log.json) | - ## Citation If you use this work or benchmark in your research, please cite this project. -``` +```latex @misc{rossi2020novel, title={A novel Region of Interest Extraction Layer for Instance Segmentation}, author={Leonardo Rossi and Akbar Karimi and Andrea Prati}, diff --git a/configs/guided_anchoring/README.md b/configs/guided_anchoring/README.md index 3bd1121b950..e8b415b79a4 100644 --- a/configs/guided_anchoring/README.md +++ b/configs/guided_anchoring/README.md @@ -4,7 +4,7 @@ We provide config files to reproduce the results in the CVPR 2019 paper for [Region Proposal by Guided Anchoring](https://arxiv.org/abs/1901.03278). -``` +```latex @inproceedings{wang2019region, title={Region Proposal by Guided Anchoring}, author={Jiaqi Wang and Kai Chen and Shuo Yang and Chen Change Loy and Dahua Lin}, @@ -24,7 +24,6 @@ The results on COCO 2017 val is shown in the below table. (results on test-dev a | GA-RPN | X-101-32x4d-FPN | pytorch | 1x | 8.5 | 10.0 | 70.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_coco/ga_rpn_x101_32x4d_fpn_1x_coco_20200220-c28d1b18.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_coco/ga_rpn_x101_32x4d_fpn_1x_coco_20200220_221326.log.json) | | GA-RPN | X-101-64x4d-FPN | pytorch | 1x | 7.1 | 7.5 | 71.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_coco/ga_rpn_x101_64x4d_fpn_1x_coco_20200225-3c6e1aa2.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_coco/ga_rpn_x101_64x4d_fpn_1x_coco_20200225_152704.log.json) | - | Method | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :------------: | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | | GA-Faster RCNN | R-50-FPN | caffe | 1x | 5.5 | | 39.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/guided_anchoring/ga_faster_r50_caffe_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_faster_r50_caffe_fpn_1x_coco/ga_faster_r50_caffe_fpn_1x_coco_20200702_000718-a11ccfe6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_faster_r50_caffe_fpn_1x_coco/ga_faster_r50_caffe_fpn_1x_coco_20200702_000718.log.json) | @@ -36,13 +35,10 @@ The results on COCO 2017 val is shown in the below table. (results on test-dev a | GA-RetinaNet | X-101-32x4d-FPN | pytorch | 1x | 6.9 | 10.6 | 40.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_coco/ga_retinanet_x101_32x4d_fpn_1x_coco_20200219-40c56caa.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_coco/ga_retinanet_x101_32x4d_fpn_1x_coco_20200219_223025.log.json) | | GA-RetinaNet | X-101-64x4d-FPN | pytorch | 1x | 9.9 | 7.7 | 41.3 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_coco/ga_retinanet_x101_64x4d_fpn_1x_coco_20200226-ef9f7f1f.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_coco/ga_retinanet_x101_64x4d_fpn_1x_coco_20200226_221123.log.json) | - - - In the Guided Anchoring paper, `score_thr` is set to 0.001 in Fast/Faster RCNN and 0.05 in RetinaNet for both baselines and Guided Anchoring. - Performance on COCO test-dev benchmark are shown as follows. - | Method | Backbone | Style | Lr schd | Aug Train | Score thr | AP | AP_50 | AP_75 | AP_small | AP_medium | AP_large | Download | | :------------: | :-------: | :---: | :-----: | :-------: | :-------: | :---: | :---: | :---: | :------: | :-------: | :------: | :------: | | GA-Faster RCNN | R-101-FPN | caffe | 1x | F | 0.05 | | | | | | | | diff --git a/configs/hrnet/README.md b/configs/hrnet/README.md index 450516658ae..94018380baa 100644 --- a/configs/hrnet/README.md +++ b/configs/hrnet/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{SunXLW19, title={Deep High-Resolution Representation Learning for Human Pose Estimation}, author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang}, @@ -22,7 +22,6 @@ ## Results and Models - ### Faster R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | @@ -45,7 +44,6 @@ | HRNetV2p-W40 | pytorch | 1x | 10.9 | | 42.1 | 37.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco/mask_rcnn_hrnetv2p_w40_1x_coco_20200511_015646-66738b35.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco/mask_rcnn_hrnetv2p_w40_1x_coco_20200511_015646.log.json) | | HRNetV2p-W40 | pytorch | 2x | 10.9 | | 42.8 | 38.2 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco/mask_rcnn_hrnetv2p_w40_2x_coco_20200512_163732-aed5e4ab.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco/mask_rcnn_hrnetv2p_w40_2x_coco_20200512_163732.log.json) | - ### Cascade R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | @@ -54,7 +52,6 @@ | HRNetV2p-W32 | pytorch | 20e | 9.4 | 11.0 | 43.3 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/cascade_rcnn_hrnetv2p_w32_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w32_20e_coco/cascade_rcnn_hrnetv2p_w32_20e_coco_20200208-928455a4.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w32_20e_coco/cascade_rcnn_hrnetv2p_w32_20e_coco_20200208_160511.log.json) | | HRNetV2p-W40 | pytorch | 20e | 10.8 | | 43.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco/cascade_rcnn_hrnetv2p_w40_20e_coco_20200512_161112-75e47b04.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco/cascade_rcnn_hrnetv2p_w40_20e_coco_20200512_161112.log.json) | - ### Cascade Mask R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | @@ -71,7 +68,6 @@ | HRNetV2p-W32 | pytorch | 20e | 13.1 | 4.9 | 45.4 | 39.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/htc_hrnetv2p_w32_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/htc_hrnetv2p_w32_20e_coco/htc_hrnetv2p_w32_20e_coco_20200207-7639fa12.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/htc_hrnetv2p_w32_20e_coco/htc_hrnetv2p_w32_20e_coco_20200207_193153.log.json) | | HRNetV2p-W40 | pytorch | 20e | 14.6 | | 46.4 | 40.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/htc_hrnetv2p_w40_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/htc_hrnetv2p_w40_20e_coco/htc_hrnetv2p_w40_20e_coco_20200529_183411-417c4d5b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/htc_hrnetv2p_w40_20e_coco/htc_hrnetv2p_w40_20e_coco_20200529_183411.log.json) | - ### FCOS | Backbone | Style | GN | MS train | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | @@ -84,8 +80,6 @@ |HRNetV2p-W32| pytorch | Y | Y | 2x | 17.5 | 12.4 | 41.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco/fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco_20200314-065d37a6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco/fcos_hrnetv2p_w32_gn-head_mstrain_640-800_4x4_2x_coco_20200314_145356.log.json) | |HRNetV2p-W48| pytorch | Y | Y | 2x | 20.3 | 10.8 | 42.8 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/hrnet/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/hrnet/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco_20200314-e201886d.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/hrnet/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco/fcos_hrnetv2p_w40_gn-head_mstrain_640-800_4x4_2x_coco_20200314_150607.log.json) | - - **Note:** - The `28e` schedule in HTC indicates decreasing the lr at 24 and 27 epochs, with a total of 28 epochs. diff --git a/configs/htc/README.md b/configs/htc/README.md index 618dcbae10f..d0fa59d9acb 100644 --- a/configs/htc/README.md +++ b/configs/htc/README.md @@ -4,7 +4,7 @@ We provide config files to reproduce the results in the CVPR 2019 paper for [Hybrid Task Cascade](https://arxiv.org/abs/1901.07518). -``` +```latex @inproceedings{chen2019hybrid, title={Hybrid task cascade for instance segmentation}, author={Chen, Kai and Pang, Jiangmiao and Wang, Jiaqi and Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and Liu, Ziwei and Shi, Jianping and Ouyang, Wanli and Chen Change Loy and Dahua Lin}, @@ -18,7 +18,7 @@ We provide config files to reproduce the results in the CVPR 2019 paper for [Hyb HTC requires COCO and COCO-stuff dataset for training. You need to download and extract it in the COCO dataset path. The directory should be like this. -``` +```none mmdetection ├── mmdet ├── tools @@ -46,7 +46,7 @@ The results on COCO 2017val are shown in the below table. (results on test-dev a - In the HTC paper and COCO 2018 Challenge, `score_thr` is set to 0.001 for both baselines and HTC. - We use 8 GPUs with 2 images/GPU for R-50 and R-101 models, and 16 GPUs with 1 image/GPU for X-101 models. -If you would like to train X-101 HTC with 8 GPUs, you need to change the lr from 0.02 to 0.01. + If you would like to train X-101 HTC with 8 GPUs, you need to change the lr from 0.02 to 0.01. We also provide a powerful HTC with DCN and multi-scale training model. No testing augmentation is used. diff --git a/configs/instaboost/README.md b/configs/instaboost/README.md index 1d4dbe5951c..1017fb96303 100644 --- a/configs/instaboost/README.md +++ b/configs/instaboost/README.md @@ -2,7 +2,7 @@ Configs in this directory is the implementation for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting" and provided by the authors of the paper. InstaBoost is a data augmentation method for object detection and instance segmentation. The paper has been released on [`arXiv`](https://arxiv.org/abs/1908.07801). -``` +```latex @inproceedings{fang2019instaboost, title={Instaboost: Boosting instance segmentation via probability map guided copy-pasting}, author={Fang, Hao-Shu and Sun, Jianhua and Wang, Runzhong and Gou, Minghao and Li, Yong-Lu and Lu, Cewu}, @@ -18,7 +18,7 @@ Configs in this directory is the implementation for ICCV2019 paper "InstaBoost: You need to install `instaboostfast` before using it. -``` +```shell pip install instaboostfast ``` @@ -30,10 +30,9 @@ InstaBoost have been already integrated in the data pipeline, thus all you need ## Results and Models - - All models were trained on `coco_2017_train` and tested on `coco_2017_val` for conveinience of evaluation and comparison. In the paper, the results are obtained from `test-dev`. - - To balance accuracy and training time when using InstaBoost, models released in this page are all trained for 48 Epochs. Other training and testing configs strictly follow the original framework. - - For results and models in MMDetection V1.x, please refer to [Instaboost](https://github.com/GothicAi/Instaboost). - +- All models were trained on `coco_2017_train` and tested on `coco_2017_val` for conveinience of evaluation and comparison. In the paper, the results are obtained from `test-dev`. +- To balance accuracy and training time when using InstaBoost, models released in this page are all trained for 48 Epochs. Other training and testing configs strictly follow the original framework. +- For results and models in MMDetection V1.x, please refer to [Instaboost](https://github.com/GothicAi/Instaboost). | Network | Backbone | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :--------: | :-----: | :------: | :------------: | :------:| :-----: | :------: | :-----------------: | diff --git a/configs/legacy_1.x/README.md b/configs/legacy_1.x/README.md index 9a0bb477a1e..ae751d61d42 100644 --- a/configs/legacy_1.x/README.md +++ b/configs/legacy_1.x/README.md @@ -10,6 +10,7 @@ Due to the BC-breaking changes in MMDetection V2.0 from MMDetection V1.x, runnin To upgrade the model version, the users need to do the following steps. ### 1. Convert model weights + There are three main difference in the model weights between V1.x and V2.0 codebases. 1. Since the class order in all the detector's classification branch is reordered, all the legacy model weights need to go through the conversion process. @@ -23,10 +24,11 @@ detectors. We provide a scripts `tools/upgrade_model_version.py` to convert the python tools/upgrade_model_version.py ${OLD_MODEL_PATH} ${NEW_MODEL_PATH} --num-classes ${NUM_CLASSES} ``` + - OLD_MODEL_PATH: the path to load the model weights in 1.x version. - NEW_MODEL_PATH: the path to save the converted model weights in 2.0 version. - NUM_CLASSES: number of classes of the original model weights. Usually it is 81 for COCO dataset, 21 for VOC dataset. -The number of classes in V2.0 models should be equal to that in V1.x models - 1. + The number of classes in V2.0 models should be equal to that in V1.x models - 1. ### 2. Use configs with legacy settings diff --git a/configs/lvis/README.md b/configs/lvis/README.md index d7c106b5e25..a7d7850bb42 100644 --- a/configs/lvis/README.md +++ b/configs/lvis/README.md @@ -1,7 +1,8 @@ # LVIS dataset ## Introduction -``` + +```latex @inproceedings{gupta2019lvis, title={{LVIS}: A Dataset for Large Vocabulary Instance Segmentation}, author={Gupta, Agrim and Dollar, Piotr and Girshick, Ross}, @@ -11,16 +12,21 @@ ``` ## Common Setting + * Please follow [install guide](../../docs/install.md#install-mmdetection) to install open-mmlab forked cocoapi first. * Run following scripts to install our forked lvis-api. - ``` + + ```shell # mmlvis is fully compatible with official lvis pip install mmlvis ``` + or - ``` + + ```shell pip install -r requirements/optional.txt ``` + * All experiments use oversample strategy [here](../../docs/tutorials/new_dataset.md#class-balanced-dataset) with oversample threshold `1e-3`. * The size of LVIS v0.5 is half of COCO, so schedule `2x` in LVIS is roughly the same iterations as `1x` in COCO. diff --git a/configs/mask_rcnn/README.md b/configs/mask_rcnn/README.md index 40533b7182a..d65f170735f 100644 --- a/configs/mask_rcnn/README.md +++ b/configs/mask_rcnn/README.md @@ -1,7 +1,8 @@ # Mask R-CNN ## Introduction -``` + +```latex @article{He_2017, title={Mask R-CNN}, journal={2017 IEEE International Conference on Computer Vision (ICCV)}, @@ -28,8 +29,8 @@ | X-101-64x4d-FPN | pytorch | 2x | - | - | 42.7 | 38.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco/mask_rcnn_x101_64x4d_fpn_2x_coco_20200509_224208-39d6f70c.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_2x_coco/mask_rcnn_x101_64x4d_fpn_2x_coco_20200509_224208.log.json)| | X-101-32x8d-FPN | pytorch | 1x | - | - | 42.8 | 38.3 | | - ## Pre-trained Models + We also train some models with longer schedules and multi-scale training. The users could finetune them for downstream tasks. | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | diff --git a/configs/nas_fcos/README.md b/configs/nas_fcos/README.md index 87c58dcb9f1..420121fc00d 100644 --- a/configs/nas_fcos/README.md +++ b/configs/nas_fcos/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @article{wang2019fcos, title={Nas-fcos: Fast neural architecture search for object detection}, author={Wang, Ning and Gao, Yang and Chen, Hao and Wang, Peng and Tian, Zhi and Shen, Chunhua}, @@ -19,4 +19,5 @@ | FCOSHead | R-50 | caffe | Y | 1x | | | 38.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/nas_fcos/nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/nas_fcos/nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco/nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco_20200521-7fdcbce0.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/nas_fcos/nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco/nas_fcos_fcoshead_r50_caffe_fpn_gn-head_4x4_1x_coco_20200521.log.json) | **Notes:** + - To be consistent with the author's implementation, we use 4 GPUs with 4 images/GPU. diff --git a/configs/nas_fpn/README.md b/configs/nas_fpn/README.md index c6e0a0c9c93..d5faecf78f5 100644 --- a/configs/nas_fpn/README.md +++ b/configs/nas_fpn/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{ghiasi2019fpn, title={Nas-fpn: Learning scalable feature pyramid architecture for object detection}, author={Ghiasi, Golnaz and Lin, Tsung-Yi and Le, Quoc V}, @@ -21,5 +21,4 @@ We benchmark the new training schedule (crop training, large batch, unfrozen BN, | R-50-FPN | 50e | 12.9 | 22.9 | 37.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/nas_fpn/retinanet_r50_fpn_crop640_50e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/nas_fpn/retinanet_r50_fpn_crop640_50e_coco/retinanet_r50_fpn_crop640_50e_coco-9b953d76.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/nas_fpn/retinanet_r50_fpn_crop640_50e_coco/retinanet_r50_fpn_crop640_50e_coco_20200529_095329.log.json) | | R-50-NASFPN | 50e | 13.2 | 23.0 | 40.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/nas_fpn/retinanet_r50_nasfpn_crop640_50e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/nas_fpn/retinanet_r50_nasfpn_crop640_50e_coco/retinanet_r50_nasfpn_crop640_50e_coco-0ad1f644.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/nas_fpn/retinanet_r50_nasfpn_crop640_50e_coco/retinanet_r50_nasfpn_crop640_50e_coco_20200528_230008.log.json) | - **Note**: We find that it is unstable to train NAS-FPN and there is a small chance that results can be 3% mAP lower. diff --git a/configs/paa/README.md b/configs/paa/README.md index 19b2b4740f1..38abe0ba8b6 100644 --- a/configs/paa/README.md +++ b/configs/paa/README.md @@ -1,8 +1,7 @@ # Probabilistic Anchor Assignment with IoU Prediction for Object Detection - - ## Results and Models + We provide config files to reproduce the object detection results in the ECCV 2020 paper for Probabilistic Anchor Assignment with IoU Prediction for Object Detection. @@ -19,4 +18,5 @@ Prediction for Object Detection. | R-101-FPN | 24e | 6.2 | True | 43.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/paa/paa_r101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/paa/paa_r101_fpn_2x_coco/paa_r101_fpn_2x_coco_20200821-6829f96b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/paa/paa_r101_fpn_2x_coco/paa_r101_fpn_2x_coco_20200821-6829f96b.log.json) | **Note**: + 1. We find that the performance is unstable with 1x setting and may fluctuate by about 0.2 mAP. We report the best results. diff --git a/configs/pisa/README.md b/configs/pisa/README.md index 75e58b7acef..b03ac7ad9bd 100644 --- a/configs/pisa/README.md +++ b/configs/pisa/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @inproceedings{cao2019prime, title={Prime sample attention in object detection}, author={Cao, Yuhang and Chen, Kai and Loy, Chen Change and Lin, Dahua}, @@ -13,7 +13,6 @@ ## Results and models - | PISA | Network | Backbone | Lr schd | box AP | mask AP | Config | Download | |:----:|:-------:|:-------------------:|:-------:|:------:|:-------:|:------:|:--------:| | × | Faster R-CNN | R-50-FPN | 1x | 36.4 | | - | @@ -34,5 +33,6 @@ | √ | SSD300 | VGG16 | 1x | 31.8 | | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_ssd512_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco-247addee.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco_20200508_131030.log.json) | **Notes:** + - In the original paper, all models are trained and tested on mmdet v1.x, thus results may not be exactly the same with this release on v2.0. - It is noted PISA only modifies the training pipeline so the inference time remains the same with the baseline. diff --git a/configs/point_rend/README.md b/configs/point_rend/README.md index e946973e700..0120185f07d 100644 --- a/configs/point_rend/README.md +++ b/configs/point_rend/README.md @@ -1,7 +1,8 @@ # PointRend ## Introduction -``` + +```latex @InProceedings{kirillov2019pointrend, title={{PointRend}: Image Segmentation as Rendering}, author={Alexander Kirillov and Yuxin Wu and Kaiming He and Ross Girshick}, diff --git a/configs/regnet/README.md b/configs/regnet/README.md index 67ba03d2de9..a3d332cda03 100644 --- a/configs/regnet/README.md +++ b/configs/regnet/README.md @@ -6,7 +6,7 @@ We implement RegNetX and RegNetY models in detection systems and provide their f The pre-trained modles are converted from [model zoo of pycls](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md). -``` +```latex @article{radosavovic2020designing, title={Designing Network Design Spaces}, author={Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Dollár}, @@ -20,6 +20,7 @@ The pre-trained modles are converted from [model zoo of pycls](https://github.co ## Usage To use a regnet model, there are two steps to do: + 1. Convert the model to ResNet-style supported by MMDetection 2. Modify backbone and neck in config accordingly @@ -33,8 +34,8 @@ ResNet-style checkpoints used in MMDetection. ```bash python -u tools/regnet2mmdet.py ${PRETRAIN_PATH} ${STORE_PATH} ``` -This script convert model from `PRETRAIN_PATH` and store the converted model in `STORE_PATH`. +This script convert model from `PRETRAIN_PATH` and store the converted model in `STORE_PATH`. ### Modify config @@ -48,6 +49,7 @@ For other pre-trained models or self-implemented regnet models, the users are re ## Results ### Mask R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :---------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | | [R-50-FPN](../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py)| pytorch | 1x | 4.4 | 12.0 | 38.2 | 34.7 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205_050542.log.json) | @@ -61,6 +63,7 @@ For other pre-trained models or self-implemented regnet models, the users are re |[RegNetX-3.2GF-FPN-DCN-C3-C5](./mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco.py)| pytorch | 1x |5.0 ||40.3|36.6|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco_20200520_172726-75f40794.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco/mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco_20200520_172726.log.json) | ### Faster R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :---------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | | [R-50-FPN](../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py)| pytorch | 1x | 4.0 | 18.2 | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json) | @@ -68,6 +71,7 @@ For other pre-trained models or self-implemented regnet models, the users are re |[RegNetX-3.2GF-FPN](./faster_rcnn_regnetx-3.2GF_fpn_2x_coco.py)| pytorch | 2x | 4.5||41.1|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/faster_rcnn_regnetx-3.2GF_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/regnet/faster_rcnn_regnetx-3.2GF_fpn_2x_coco/faster_rcnn_regnetx-3.2GF_fpn_2x_coco_20200520_223955-e2081918.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/regnet/faster_rcnn_regnetx-3.2GF_fpn_2x_coco/faster_rcnn_regnetx-3.2GF_fpn_2x_coco_20200520_223955.log.json) | ### RetinaNet + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :---------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | | [R-50-FPN](../retinanet/retinanet_r50_fpn_1x_coco.py) | pytorch | 1x | 3.8 | 16.6 | 36.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet/retinanet_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r50_fpn_1x_coco/retinanet_r50_fpn_1x_coco_20200130-c2398f9e.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r50_fpn_1x_coco/retinanet_r50_fpn_1x_coco_20200130_002941.log.json) | @@ -85,6 +89,6 @@ We also train some models with longer schedules and multi-scale training. The us |Mask RCNN |[RegNetX-3.2GF-FPN](./mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco.py)| pytorch | 3x |5.0 ||43.1|38.7|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco/mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco_20200521_202221-99879813.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco/mask_rcnn_regnetx-3.2GF_fpn_mstrain_3x_coco_20200521_202221.log.json) | ### Notice + 1. The models are trained using a different weight decay, i.e., `weight_decay=5e-5` according to the setting in ImageNet training. This brings improvement of at least 0.7 AP absolute but does not improve the model using ResNet-50. -2. RetinaNets using RegNets are trained with learning rate 0.02 with gradient clip. We find that using learning rate 0.02 could improve the results by at least 0.7 AP absolute and gradient clip is necessary to stabilize the training. -However, this does not improve the performance of ResNet-50-FPN RetinaNet. +2. RetinaNets using RegNets are trained with learning rate 0.02 with gradient clip. We find that using learning rate 0.02 could improve the results by at least 0.7 AP absolute and gradient clip is necessary to stabilize the training. However, this does not improve the performance of ResNet-50-FPN RetinaNet. diff --git a/configs/res2net/README.md b/configs/res2net/README.md index b326ba4a5ee..3275fdfbc9d 100644 --- a/configs/res2net/README.md +++ b/configs/res2net/README.md @@ -14,9 +14,10 @@ We propose a novel building block for CNNs, namely Res2Net, by constructing hier Compared with other backbone networks, Res2Net requires fewer parameters and FLOPs. **Note:** + - GFLOPs for classification are calculated with image size (224x224). -``` +```latex @article{gao2019res2net, title={Res2Net: A New Multi-scale Backbone Architecture}, author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip}, @@ -25,28 +26,38 @@ Compared with other backbone networks, Res2Net requires fewer parameters and FLO doi={10.1109/TPAMI.2019.2938758}, } ``` + ## Results and Models + ### Faster R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | -|R2-101-FPN | pytorch | 2x | 7.4 | - | 43.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/faster_rcnn_r2_101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/faster_rcnn_r2_101_fpn_2x_coco/faster_rcnn_r2_101_fpn_2x_coco-175f1da6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/faster_rcnn_r2_101_fpn_2x_coco/faster_rcnn_r2_101_fpn_2x_coco_20200514_231734.log.json) | +|R2-101-FPN | pytorch | 2x | 7.4 | - | 43.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/faster_rcnn_r2_101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/faster_rcnn_r2_101_fpn_2x_coco/faster_rcnn_r2_101_fpn_2x_coco-175f1da6.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/faster_rcnn_r2_101_fpn_2x_coco/faster_rcnn_r2_101_fpn_2x_coco_20200514_231734.log.json) | + ### Mask R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | -|R2-101-FPN | pytorch | 2x | 7.9 | - | 43.6 | 38.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/mask_rcnn_r2_101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/mask_rcnn_r2_101_fpn_2x_coco/mask_rcnn_r2_101_fpn_2x_coco-17f061e8.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/mask_rcnn_r2_101_fpn_2x_coco/mask_rcnn_r2_101_fpn_2x_coco_20200515_002413.log.json) | +|R2-101-FPN | pytorch | 2x | 7.9 | - | 43.6 | 38.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/mask_rcnn_r2_101_fpn_2x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/mask_rcnn_r2_101_fpn_2x_coco/mask_rcnn_r2_101_fpn_2x_coco-17f061e8.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/mask_rcnn_r2_101_fpn_2x_coco/mask_rcnn_r2_101_fpn_2x_coco_20200515_002413.log.json) | + ### Cascade R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | -|R2-101-FPN | pytorch | 20e | 7.8 | - | 45.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/cascade_rcnn_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_rcnn_r2_101_fpn_20e_coco/cascade_rcnn_r2_101_fpn_20e_coco-f4b7b7db.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_rcnn_r2_101_fpn_20e_coco/cascade_rcnn_r2_101_fpn_20e_coco_20200515_091644.log.json) | +|R2-101-FPN | pytorch | 20e | 7.8 | - | 45.7 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/cascade_rcnn_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_rcnn_r2_101_fpn_20e_coco/cascade_rcnn_r2_101_fpn_20e_coco-f4b7b7db.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_rcnn_r2_101_fpn_20e_coco/cascade_rcnn_r2_101_fpn_20e_coco_20200515_091644.log.json) | + ### Cascade Mask R-CNN + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | -R2-101-FPN | pytorch | 20e | 9.5 | - | 46.4 | 40.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco/cascade_mask_rcnn_r2_101_fpn_20e_coco-8a7b41e1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco/cascade_mask_rcnn_r2_101_fpn_20e_coco_20200515_091645.log.json) | +R2-101-FPN | pytorch | 20e | 9.5 | - | 46.4 | 40.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco/cascade_mask_rcnn_r2_101_fpn_20e_coco-8a7b41e1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/cascade_mask_rcnn_r2_101_fpn_20e_coco/cascade_mask_rcnn_r2_101_fpn_20e_coco_20200515_091645.log.json) | + ### Hybrid Task Cascade (HTC) + | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | -| R2-101-FPN | pytorch | 20e | - | - | 47.5 | 41.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/htc_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/htc_r2_101_fpn_20e_coco/htc_r2_101_fpn_20e_coco-3a8d2112.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/htc_r2_101_fpn_20e_coco/htc_r2_101_fpn_20e_coco_20200515_150029.log.json) | - +| R2-101-FPN | pytorch | 20e | - | - | 47.5 | 41.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/res2net/htc_r2_101_fpn_20e_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/res2net/htc_r2_101_fpn_20e_coco/htc_r2_101_fpn_20e_coco-3a8d2112.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/res2net/htc_r2_101_fpn_20e_coco/htc_r2_101_fpn_20e_coco_20200515_150029.log.json) | - Res2Net ImageNet pretrained models are in [Res2Net-PretrainedModels](https://github.com/Res2Net/Res2Net-PretrainedModels). - More applications of Res2Net are in [Res2Net-Github](https://github.com/Res2Net/). diff --git a/configs/resnest/README.md b/configs/resnest/README.md index 07c916407e8..4d29c2a0c12 100644 --- a/configs/resnest/README.md +++ b/configs/resnest/README.md @@ -17,26 +17,26 @@ year={2020} | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | -|S-50-FPN | pytorch | 1x | 4.8 | - | 42.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20200926_125502-20289c16.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20200926_125502.log.json) | -|S-101-FPN | pytorch | 1x | 7.1 | - | 44.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201006_021058-421517f1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201006_021058.log.json) | +|S-50-FPN | pytorch | 1x | 4.8 | - | 42.0 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20200926_125502-20289c16.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20200926_125502.log.json) | +|S-101-FPN | pytorch | 1x | 7.1 | - | 44.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201006_021058-421517f1.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/faster_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201006_021058.log.json) | ### Mask R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | -|S-50-FPN | pytorch | 1x | 5.5 | - | 42.6 | 38.1 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco_20200926_125503-8a2c3d47.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco-20200926_125503.log.json) | -|S-101-FPN | pytorch | 1x | 7.8 | - | 45.2 | 40.2 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco_20201005_215831-af60cdf9.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco-20201005_215831.log.json) | +|S-50-FPN | pytorch | 1x | 5.5 | - | 42.6 | 38.1 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco_20200926_125503-8a2c3d47.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco-20200926_125503.log.json) | +|S-101-FPN | pytorch | 1x | 7.8 | - | 45.2 | 40.2 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco_20201005_215831-af60cdf9.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco-20201005_215831.log.json) | ### Cascade R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :------: | :--------: | -|S-50-FPN | pytorch | 1x | - | - | 44.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201122_213640-763cc7b5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201005_113242.log.json) | -|S-101-FPN | pytorch | 1x | 8.4 | - | 46.8 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201005_113242-b9459f8f.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201122_213640.log.json) | +|S-50-FPN | pytorch | 1x | - | - | 44.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201122_213640-763cc7b5.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201005_113242.log.json) | +|S-101-FPN | pytorch | 1x | 8.4 | - | 46.8 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s101_fpn_syncbn-backbone+head_mstrain-range_1x_coco_20201005_113242-b9459f8f.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco/cascade_rcnn_s50_fpn_syncbn-backbone+head_mstrain-range_1x_coco-20201122_213640.log.json) | ### Cascade Mask R-CNN | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download | | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: | -|S-50-FPN | pytorch | 1x | - | - | 45.4 | 39.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco_20201122_104428-99eca4c7.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco-20201122_104428.log.json) | -|S-101-FPN | pytorch | 1x | 10.5 | - | 47.7 | 41.4 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco_20201005_113243-42607475.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco-20201005_113243.log.json) | +|S-50-FPN | pytorch | 1x | - | - | 45.4 | 39.5 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco_20201122_104428-99eca4c7.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s50_fpn_syncbn-backbone+head_mstrain_1x_coco-20201122_104428.log.json) | +|S-101-FPN | pytorch | 1x | 10.5 | - | 47.7 | 41.4 |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco_20201005_113243-42607475.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/resnest/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco/cascade_mask_rcnn_s101_fpn_syncbn-backbone+head_mstrain_1x_coco-20201005_113243.log.json) | diff --git a/configs/retinanet/README.md b/configs/retinanet/README.md index b7953ffc9f7..ffb7b9f949d 100644 --- a/configs/retinanet/README.md +++ b/configs/retinanet/README.md @@ -1,7 +1,8 @@ # Focal Loss for Dense Object Detection ## Introduction -``` + +```latex @inproceedings{lin2017focal, title={Focal loss for dense object detection}, author={Lin, Tsung-Yi and Goyal, Priya and Girshick, Ross and He, Kaiming and Doll{\'a}r, Piotr}, diff --git a/configs/rpn/README.md b/configs/rpn/README.md index 773d5e3a3e5..09aff132c54 100644 --- a/configs/rpn/README.md +++ b/configs/rpn/README.md @@ -1,7 +1,8 @@ # Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks ## Introduction -``` + +```latex @inproceedings{ren2015faster, title={Faster r-cnn: Towards real-time object detection with region proposal networks}, author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian}, diff --git a/configs/sabl/README.md b/configs/sabl/README.md index 495324c7667..85c3c57d42b 100644 --- a/configs/sabl/README.md +++ b/configs/sabl/README.md @@ -4,7 +4,7 @@ We provide config files to reproduce the object detection results in the ECCV 2020 Spotlight paper for [Side-Aware Boundary Localization for More Precise Object Detection](https://arxiv.org/abs/1912.04260). -``` +```latex @inproceedings{Wang_2020_ECCV, title = {Side-Aware Boundary Localization for More Precise Object Detection}, author = {Jiaqi Wang and Wenwei Zhang and Yuhang Cao and Kai Chen and Jiangmiao Pang and Tao Gong and Jianping Shi and Chen Change Loy and Dahua Lin}, @@ -18,7 +18,6 @@ We provide config files to reproduce the object detection results in the ECCV 20 The results on COCO 2017 val is shown in the below table. (results on test-dev are usually slightly higher than val). Single-scale testing (1333x800) is adopted in all results. - | Method | Backbone | Lr schd | ms-train | box AP | Config | Download | | :----------------: | :-------: | :-----: | :------: | :----: | :----------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | | SABL Faster R-CNN | R-50-FPN | 1x | N | 39.9 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_faster_rcnn_r50_fpn_1x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r50_fpn_1x_coco/sabl_faster_rcnn_r50_fpn_1x_coco-e867595b.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r50_fpn_1x_coco/20200830_130324.log.json) | diff --git a/configs/scratch/README.md b/configs/scratch/README.md index a47ed52af08..18f638203c9 100644 --- a/configs/scratch/README.md +++ b/configs/scratch/README.md @@ -2,7 +2,7 @@ ## Introduction -``` +```latex @article{he2018rethinking, title={Rethinking imagenet pre-training}, author={He, Kaiming and Girshick, Ross and Doll{\'a}r, Piotr}, @@ -19,4 +19,5 @@ | Mask R-CNN | R-50-FPN | pytorch | 6x | 41.2 | 37.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/scratch/mask_rcnn_r50_fpn_gn-all_scratch_6x_coco.py) | [model](http://download.openmmlab.com/mmdetection/v2.0/scratch/mask_rcnn_r50_fpn_gn-all_scratch_6x_coco/scratch_mask_rcnn_r50_fpn_gn_6x_bbox_mAP-0.412__segm_mAP-0.374_20200201_193051-1e190a40.pth) | [log](http://download.openmmlab.com/mmdetection/v2.0/scratch/mask_rcnn_r50_fpn_gn-all_scratch_6x_coco/scratch_mask_rcnn_r50_fpn_gn_6x_20200201_193051.log.json) | Note: + - The above models are trained with 16 GPUs. diff --git a/configs/ssd/README.md b/configs/ssd/README.md index 582292f2dbb..e0d17744c71 100644 --- a/configs/ssd/README.md +++ b/configs/ssd/README.md @@ -1,7 +1,8 @@ # SSD: Single Shot MultiBox Detector ## Introduction -``` + +```latex @article{Liu_2016, title={SSD: Single Shot MultiBox Detector}, journal={ECCV}, diff --git a/configs/vfnet/README.md b/configs/vfnet/README.md index 3d6aef3fbc8..f5cc22ecfa1 100644 --- a/configs/vfnet/README.md +++ b/configs/vfnet/README.md @@ -1,6 +1,7 @@ # VarifocalNet: An IoU-aware Dense Object Detector ## Introduction + **VarifocalNet (VFNet)** learns to predict the IoU-aware classification score which mixes the object presence confidence and localization accuracy together as the detection score for a bounding box. The learning is supervised by the proposed Varifocal Loss (VFL), based on a new star-shaped bounding box feature representation (the features at nine yellow sampling points). Given the new representation, the object localization accuracy is further improved by refining the initially regressed bounding box. The full paper is available at: [https://arxiv.org/abs/2008.13367](https://arxiv.org/abs/2008.13367).
@@ -10,7 +11,7 @@ ## Citing VarifocalNet -``` +```latex @article{zhang2020varifocalnet, title={VarifocalNet: An IoU-aware Dense Object Detector}, author={Zhang, Haoyang and Wang, Ying and Dayoub, Feras and S{\"u}nderhauf, Niko}, @@ -32,8 +33,8 @@ | X-101-32x4d | pytorch | Y | Y | 2x | - | 49.7 | 50.0 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py) | [model](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmdetection/v2.0/vfnet/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco_20201027pth-d300a6fc.pth) | [log](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmdetection/v2.0/vfnet/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco/vfnet_x101_32x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.json)| | X-101-64x4d | pytorch | Y | Y | 2x | - | 50.4 | 50.8 | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.py) | [model](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmdetection/v2.0/vfnet/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco_20201027pth-b5f6da5e.pth) | [log](https://openmmlab.oss-cn-hangzhou.aliyuncs.com/mmdetection/v2.0/vfnet/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco/vfnet_x101_64x4d_fpn_mdconv_c3-c5_mstrain_2x_coco.json)| - **Notes:** + - The MS-train scale range is 1333x[480:960] (`range` mode) and the inference scale keeps 1333x800. - DCN means using `DCNv2` in both backbone and head. - Inference time will be updated soon. diff --git a/configs/yolact/README.md b/configs/yolact/README.md index 37d2b46e26b..fea128e3f78 100644 --- a/configs/yolact/README.md +++ b/configs/yolact/README.md @@ -1,4 +1,5 @@ # **Y**ou **O**nly **L**ook **A**t **C**oefficien**T**s + ``` ██╗ ██╗ ██████╗ ██╗ █████╗ ██████╗████████╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔══██╗██╔════╝╚══██╔══╝ @@ -9,13 +10,15 @@ ``` A simple, fully convolutional model for real-time instance segmentation. This is the code for our paper: - - [YOLACT: Real-time Instance Segmentation](https://arxiv.org/abs/1904.02689) + +- [YOLACT: Real-time Instance Segmentation](https://arxiv.org/abs/1904.02689) -#### For a real-time demo, check out our ICCV video: +For a real-time demo, check out our ICCV video: [![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/0pMfmo8qfpQ/0.jpg)](https://www.youtube.com/watch?v=0pMfmo8qfpQ) -# Evaluation +## Evaluation + Here are our YOLACT models along with their FPS on a Titan Xp and mAP on COCO's `val`: | Image Size | GPU x BS | Backbone | *FPS | mAP | Weights | Configs | Download | @@ -26,19 +29,24 @@ Here are our YOLACT models along with their FPS on a Titan Xp and mAP on COCO's *Note: The FPS is evaluated by the [original implementation](https://github.com/dbolya/yolact). When calculating FPS, only the model inference time is taken into account. Data loading and post-processing operations such as converting masks to RLE code, generating COCO JSON results, image rendering are not included. -# Training +## Training + All the aforementioned models are trained with a single GPU. It typically takes ~12GB VRAM when using resnet-101 as the backbone. If you want to try multiple GPUs training, you may have to modify the configuration files accordingly, such as adjusting the training schedule and freezing batch norm. + ```Shell # Trains using the resnet-101 backbone with a batch size of 8 on a single GPU. ./tools/dist_train.sh configs/yolact/yolact_r101.py 1 ``` -# Testing +## Testing + Please refer to [mmdetection/docs/getting_started.md](https://github.com/open-mmlab/mmdetection/blob/master/docs/getting_started.md#inference-with-pretrained-models). -# Citation +## Citation + If you use YOLACT or this code base in your work, please cite -``` + +```latex @inproceedings{yolact-iccv2019, author = {Daniel Bolya and Chong Zhou and Fanyi Xiao and Yong Jae Lee}, title = {YOLACT: {Real-time} Instance Segmentation}, @@ -48,7 +56,8 @@ If you use YOLACT or this code base in your work, please cite ```