Merge branch 'master' of https://github.com/open-mmlab/mmdetection in…

…to lad
open-mmlab · Nov 16, 2021 · 7732087 · 7732087
2 parents 7949e17 + c76ab0e
commit 7732087
Show file tree

Hide file tree

Showing 82 changed files with 2,885 additions and 1,906 deletions.
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -167,7 +167,7 @@ jobs:
 
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8, 3.9-dev]
+        python-version: [3.6, 3.7, 3.8, 3.9]
         torch: [1.9.0+cu102]
         include:
           - torch: 1.9.0+cu102
@@ -181,9 +181,17 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+      # Add ppa source repo for python3.9.
+      - name: Add python3.9 source
+        run: |
+          apt-get update && apt-get install -y software-properties-common
+          add-apt-repository -y ppa:deadsnakes/ppa
+        if: ${{matrix.python-version == '3.9'}}
+      # Install python-dev for some packages which require libpython3.Xm.
+      # Github's setup-python cannot install python3.9-dev, so we have to use apt install.
+      # Set DEBIAN_FRONTEND=noninteractive to avoid some interactions.
       - name: Install python-dev
-        run: apt-get update && apt-get install -y python${{matrix.python-version}}-dev
-        if: ${{matrix.python-version != '3.9-dev'}}
+        run: apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends python${{matrix.python-version}}-dev
       - name: Install system dependencies
         run: |
           apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6
@@ -196,7 +204,7 @@ jobs:
         run: python -m pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html
       - name: Install dependencies for compiling onnx when python=3.9
         run: python -m pip install protobuf && apt-get update && apt-get -y install libprotobuf-dev protobuf-compiler cmake
-        if: ${{matrix.python-version == '3.9-dev'}}
+        if: ${{matrix.python-version == '3.9'}}
       - name: Install mmdet dependencies
         run: |
           python -V

diff --git a/README.md b/README.md
@@ -13,10 +13,10 @@
   <img src="https://user-images.githubusercontent.com/12907710/137271636-56ba1cd2-b110-4812-8221-b4c120320aa9.png"/>
 
 
-[📘Documentation](https://mmdetection.readthedocs.io/en/v2.17.0/) |
-[🛠️Installation](https://mmdetection.readthedocs.io/en/v2.17.0/get_started.html) |
-[👀Model Zoo](https://mmdetection.readthedocs.io/zh_CN/v2.17.0/model_zoo.html) |
-[🆕Update News](https://mmdetection.readthedocs.io/en/v2.17.0/changelog.html) |
+[📘Documentation](https://mmdetection.readthedocs.io/en/v2.18.1/) |
+[🛠️Installation](https://mmdetection.readthedocs.io/en/v2.18.1/get_started.html) |
+[👀Model Zoo](https://mmdetection.readthedocs.io/zh_CN/v2.18.1/model_zoo.html) |
+[🆕Update News](https://mmdetection.readthedocs.io/en/v2.18.1/changelog.html) |
 [🚀Ongoing Projects](https://github.com/open-mmlab/mmdetection/projects) |
 [🤔Reporting Issues](https://github.com/open-mmlab/mmdetection/issues/new/choose)
 
@@ -60,10 +60,10 @@ This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
-**2.17.0** was released in 28/09/2021:
-- Support PVT, PVTv2 and SOLO.
-- Support large scale jittering and New Mask R-CNN baselines.
-- Speed up YOLOv3 inference.
+**2.18.1** was released in 15/11/2021:
+- Release [QueryInst](http://arxiv.org/abs/2105.01928) pre-trained weights.
+- Support plot confusion matrix.
+- Fix SpatialReductionAttention in PVT and fix trunc_normal_init in both PVT and Swin-Transformer.
 
 Please refer to [changelog.md](docs/changelog.md) for details and release history.
 

diff --git a/README_zh-CN.md b/README_zh-CN.md
@@ -13,10 +13,10 @@
   <img src="https://user-images.githubusercontent.com/12907710/137271636-56ba1cd2-b110-4812-8221-b4c120320aa9.png"/>
 
 
-[📘使用文档](https://mmdetection.readthedocs.io/zh_CN/v2.17.0/) |
-[🛠️安装教程](https://mmdetection.readthedocs.io/zh_CN/v2.17.0/get_started.html) |
-[👀模型库](https://mmdetection.readthedocs.io/zh_CN/v2.17.0/model_zoo.html) |
-[🆕更新日志](https://mmdetection.readthedocs.io/en/v2.17.0/changelog.html) |
+[📘使用文档](https://mmdetection.readthedocs.io/zh_CN/v2.18.1/) |
+[🛠️安装教程](https://mmdetection.readthedocs.io/zh_CN/v2.18.1/get_started.html) |
+[👀模型库](https://mmdetection.readthedocs.io/zh_CN/v2.18.1/model_zoo.html) |
+[🆕更新日志](https://mmdetection.readthedocs.io/en/v2.18.1/changelog.html) |
 [🚀进行中的项目](https://github.com/open-mmlab/mmdetection/projects) |
 [🤔报告问题](https://github.com/open-mmlab/mmdetection/issues/new/choose)
 
@@ -59,10 +59,10 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
 
 ## 更新日志
 
-最新的 **2.17.0** 版本已经在2021.09.28发布:
-- 支持了 PVT, PVTv2 and SOLO。
-- 支持了 large scale jittering 并且增加了新的 Mask R-CNN 基线模型。
-- 提升 YOLOv3 的推理速度。
+最新的 **2.18.1** 版本已经在2021.11.15发布:
+- 发布了 [QueryInst](http://arxiv.org/abs/2105.01928) 的预训练模型。
+- 支持绘制混淆矩阵。
+- 修复了 PVT 中的 SpatialReductionAttention 以及 PVT 和 Swin-Transformer 中 trunc_normal_init 的错误用法。
 
 如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/changelog.md)。
 

diff --git a/configs/groie/README.md b/configs/groie/README.md
@@ -25,9 +25,6 @@ performance.
 ## Results and models
 
 The results on COCO 2017 minival (5k images) are shown in the below table.
-You can find
-[here](https://drive.google.com/drive/folders/19ssstbq_h0Z1cgxHmJYFO8s1arf3QJbT)
-the trained models.
 
 ### Application of GRoIE to different architectures
 
@@ -42,24 +39,24 @@ the trained models.
 | R-50-FPN  | GC-Net           |   1x    |  40.7  |  36.5   | [config](../gcnet/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/gcnet/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco_20200202-50b90e5c.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/gcnet/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco_20200202_085547.log.json) |
 | R-50-FPN  | + GRoIE          |   1x    |  41.0  |  37.8   | [config](./mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200604_211715-42eb79e1.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/groie/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco/mask_rcnn_r50_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco_20200604_211715-42eb79e1.pth) |
 | R-101-FPN | GC-Net           |   1x    |  42.2  |  37.8   | [config](../gcnet/mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_1x_coco.py) | [model](https://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) &#124; [log](https://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](https://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) &#124; [log](https://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) |
+| R-101-FPN | + GRoIE          |   1x    |  42.6  |  38.7   | [config](./mask_rcnn_r101_fpn_syncbn-backbone_r4_gcb_c3-c5_groie_1x_coco.py)| [model](https://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) &#124; [log](https://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},
-    year={2020},
-    eprint={2004.13665},
-    archivePrefix={arXiv},
-    primaryClass={cs.CV}
+@inproceedings{rossi2021novel,
+  title={A novel region of interest extraction layer for instance segmentation},
+  author={Rossi, Leonardo and Karimi, Akbar and Prati, Andrea},
+  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
+  pages={2203--2209},
+  year={2021},
+  organization={IEEE}
 }
 ```
 
 ## Contact
 
-The implementation of GROI is currently maintained by
+The implementation of GRoIE is currently maintained by
 [Leonardo Rossi](https://github.com/hachreak/).
diff --git a/configs/queryinst/README.md b/configs/queryinst/README.md
@@ -19,8 +19,8 @@
 
 | Model        | Backbone  | Style   | Lr schd | Number of Proposals |Multi-Scale| RandomCrop  | box AP  | mask AP  | Config | Download |
 |:------------:|:---------:|:-------:|:-------:|:-------:            |:-------: |:---------:|:------:|:------:|:------:|:--------:|
-| QueryInst | R-50-FPN  | pytorch | 1x      |   100               | False     |  False     |  42.0  |  37.5  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_1x_coco.py) | [model]() &#124; [log]() |
-| QueryInst | R-50-FPN  | pytorch | 3x      |   100               | True     |   False     |  44.8  |  39.8  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_mstrain_480-800_3x_coco.py) | [model]() &#124; [log]() |
-| QueryInst | R-50-FPN  | pytorch | 3x      |   300               | True      |  True      |  47.5  |  41.7  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py) | [model]() &#124; [log]() |
-| QueryInst | R-101-FPN | pytorch | 3x      |   100               | True      |  False     |  46.4  |  41.0  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r101_fpn_mstrain_480-800_3x_coco.py) | [model]() &#124; [log]() |
-| QueryInst | R-101-FPN | pytorch | 3x      |   300               | True      |  True      |  49.0  |  42.9  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py) | [model]() &#124; [log]() |
+| QueryInst | R-50-FPN  | pytorch | 1x      |   100               | False     |  False     |  42.0  |  37.5  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_1x_coco/queryinst_r50_fpn_1x_coco_20210907_084916-5a8f1998.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_1x_coco/queryinst_r50_fpn_1x_coco_20210907_084916.log.json) |
+| QueryInst | R-50-FPN  | pytorch | 3x      |   100               | True     |   False     |  44.8  |  39.8  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_mstrain_480-800_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_mstrain_480-800_3x_coco/queryinst_r50_fpn_mstrain_480-800_3x_coco_20210901_103643-7837af86.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_mstrain_480-800_3x_coco/queryinst_r50_fpn_mstrain_480-800_3x_coco_20210901_103643.log.json) |
+| QueryInst | R-50-FPN  | pytorch | 3x      |   300               | True      |  True      |  47.5  |  41.7  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_101802-85cffbd8.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_101802.log.json) |
+| QueryInst | R-101-FPN | pytorch | 3x      |   100               | True      |  False     |  46.4  |  41.0  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r101_fpn_mstrain_480-800_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_mstrain_480-800_3x_coco/queryinst_r101_fpn_mstrain_480-800_3x_coco_20210904_104048-91f9995b.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_mstrain_480-800_3x_coco/queryinst_r101_fpn_mstrain_480-800_3x_coco_20210904_104048.log.json) |
+| QueryInst | R-101-FPN | pytorch | 3x      |   300               | True      |  True      |  49.0  |  42.9  |  [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_153621-76cce59f.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_153621.log.json) |
diff --git a/configs/queryinst/metafile.yml b/configs/queryinst/metafile.yml
@@ -33,7 +33,7 @@ Models:
         Dataset: COCO
         Metrics:
           mask AP: 37.5
-    Weights:
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_1x_coco/queryinst_r50_fpn_1x_coco_20210907_084916-5a8f1998.pth
 
   - Name: queryinst_r50_fpn_mstrain_480-800_3x_coco
     In Collection: QueryInst
@@ -49,7 +49,7 @@ Models:
         Dataset: COCO
         Metrics:
           mask AP: 39.8
-    Weights:
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_mstrain_480-800_3x_coco/queryinst_r50_fpn_mstrain_480-800_3x_coco_20210901_103643-7837af86.pth
 
   - Name: queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco
     In Collection: QueryInst
@@ -65,7 +65,7 @@ Models:
         Dataset: COCO
         Metrics:
           mask AP: 41.7
-    Weights:
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_101802-85cffbd8.pth
 
   - Name: queryinst_r101_fpn_mstrain_480-800_3x_coco
     In Collection: QueryInst
@@ -81,7 +81,7 @@ Models:
         Dataset: COCO
         Metrics:
           mask AP: 41.0
-    Weights:
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_mstrain_480-800_3x_coco/queryinst_r101_fpn_mstrain_480-800_3x_coco_20210904_104048-91f9995b.pth
 
   - Name: queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco
     In Collection: QueryInst
@@ -97,4 +97,4 @@ Models:
         Dataset: COCO
         Metrics:
           mask AP: 42.9
-    Weights:
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_153621-76cce59f.pth
diff --git a/demo/MMDet_Tutorial.ipynb b/demo/MMDet_Tutorial.ipynb
diff --git a/docker/Dockerfile b/docker/Dockerfile
@@ -13,7 +13,7 @@ RUN apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build
     && rm -rf /var/lib/apt/lists/*
 
 # Install MMCV
-RUN pip install mmcv-full==1.3.14 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.6.0/index.html
+RUN pip install mmcv-full==1.3.17 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.6.0/index.html
 
 # Install MMDetection
 RUN conda clean --all

diff --git a/docker/serve/Dockerfile b/docker/serve/Dockerfile
@@ -3,8 +3,8 @@ ARG CUDA="10.1"
 ARG CUDNN="7"
 FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
 
-ARG MMCV="1.3.14"
-ARG MMDET="2.17.0"
+ARG MMCV="1.3.17"
+ARG MMDET="2.18.1"
 
 ENV PYTHONUNBUFFERED TRUE
 

diff --git a/docs/1_exist_data_model.md b/docs/1_exist_data_model.md
@@ -300,7 +300,7 @@ Assuming that you have already downloaded the checkpoints to the directory `chec
 
    ```shell
    python tools/test.py \
-       configs/faster_rcnn/faster_rcnn_r50_fpn_1x.py \
+       configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \
        checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \
        --show-dir faster_rcnn_r50_fpn_1x_results
    ```

diff --git a/docs/2_new_data_model.md b/docs/2_new_data_model.md
@@ -257,7 +257,7 @@ For more detailed usages, please refer to the [Case 1](1_exist_data_model.md).
 To test the trained model, you can simply run
 
 ```shell
-python tools/test.py configs/balloon/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_balloon.py work_dirs/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_balloon.py/latest.pth --eval bbox segm
+python tools/test.py configs/balloon/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_balloon.py work_dirs/mask_rcnn_r50_caffe_fpn_mstrain-poly_1x_balloon/latest.pth --eval bbox segm
 ```
 
 For more detailed usages, please refer to the [Case 1](1_exist_data_model.md).