Skip to content

Commit 61dd8d5

Browse files
BIGWangYuDongRangeKing
BIGWangYuDong
and
RangeKing
authored
Bump version to 3.0.0rc6 (#9817)
Co-authored-by: Range King <RangeKingHZ@gmail.com>
1 parent 33d073b commit 61dd8d5

File tree

11 files changed

+133
-25
lines changed

11 files changed

+133
-25
lines changed

‎.circleci/test.yml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -69,7 +69,7 @@ jobs:
6969
command: |
7070
python -m pip install git+ssh://git@github.com/open-mmlab/mmengine.git@main
7171
pip install -U openmim
72-
mim install 'mmcv >= 2.0.0rc0'
72+
mim install 'mmcv >= 2.0.0rc4'
7373
pip install -r requirements/tests.txt -r requirements/optional.txt
7474
pip install --force-reinstall pycocotools
7575
pip install albumentations>=0.3.2 --no-binary imgaug,albumentations
@@ -117,7 +117,7 @@ jobs:
117117
command: |
118118
docker exec mmdetection pip install -e /mmengine
119119
docker exec mmdetection pip install -U openmim
120-
docker exec mmdetection mim install 'mmcv >= 2.0.0rc0'
120+
docker exec mmdetection mim install 'mmcv >= 2.0.0rc4'
121121
docker exec mmdetection pip install -r requirements/tests.txt -r requirements/optional.txt
122122
docker exec mmdetection pip install pycocotools
123123
docker exec mmdetection pip install albumentations>=0.3.2 --no-binary imgaug,albumentations

‎README.md‎

Lines changed: 17 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -108,10 +108,14 @@ We are excited to announce our latest work on real-time object recognition tasks
108108
<img src="https://user-images.githubusercontent.com/12907710/208044554-1e8de6b5-48d8-44e4-a7b5-75076c7ebb71.png"/>
109109
</div>
110110

111-
**v3.0.0rc5** was released in 26/12/2022:
111+
**v3.0.0rc6** was released in 24/2/2023:
112112

113-
- Support [RTMDet](https://arxiv.org/abs/2212.07784) instance segmentation models. The technical report of RTMDet is on [arxiv](https://arxiv.org/abs/2212.07784)
114-
- Support SSHContextModule in paper [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979)
113+
- Support [Boxinst](configs/boxinst), [Objects365 Dataset](configs/objects365), and [Separated and Occluded COCO metric](docs/en/user_guides/useful_tools.md#coco-separated--occluded-mask-metric)
114+
- Support [ConvNeXt-V2](projects/ConvNeXt-V2), [DiffusionDet](projects/DiffusionDet), and inference of [EfficientDet](projects/EfficientDet) and [Detic](projects/Detic) in `Projects`
115+
- Refactor [DETR](configs/detr) series and support [Conditional-DETR](configs/conditional_detr), [DAB-DETR](configs/dab_detr), and [DINO](configs/dino)
116+
- Support `DetInferencer` for inference, Test Time Augmentation, and automatically importing modules from registry
117+
- Support RTMDet-Ins ONNXRuntime and TensorRT [deployment](configs/rtmdet/README.md#deployment-tutorial)
118+
- Support [calculating FLOPs of detectors](docs/en/user_guides/useful_tools.md#Model-Complexity)
115119

116120
## Installation
117121

@@ -220,6 +224,12 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
220224
<li><a href="configs/tood">TOOD (ICCV'2021)</a></li>
221225
<li><a href="configs/ddod">DDOD (ACM MM'2021)</a></li>
222226
<li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li>
227+
<li><a href="configs/conditional_detr">Conditional DETR (ICCV'2021)</a></li>
228+
<li><a href="configs/dab_detr">DAB-DETR (ICLR'2022)</a></li>
229+
<li><a href="configs/dino">DINO (ICLR'2023)</a></li>
230+
<li><a href="projects/DiffusionDet">DiffusionDet (ArXiv'2023)</a></li>
231+
<li><a href="projects/EfficientDet">EfficientDet (CVPR'2020)</a></li>
232+
<li><a href="projects/Detic">Detic (ECCV'2022)</a></li>
223233
</ul>
224234
</td>
225235
<td>
@@ -237,9 +247,10 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
237247
<li><a href="configs/scnet">SCNet (AAAI'2021)</a></li>
238248
<li><a href="configs/queryinst">QueryInst (ICCV'2021)</a></li>
239249
<li><a href="configs/mask2former">Mask2Former (ArXiv'2021)</a></li>
240-
<li><a href="configs/condinst">CondInst (ECCV 2020)</a></li>
241-
<li><a href="projects/SparseInst">SparseInst (CVPR 2022)</a></li>
250+
<li><a href="configs/condinst">CondInst (ECCV'2020)</a></li>
251+
<li><a href="projects/SparseInst">SparseInst (CVPR'2022)</a></li>
242252
<li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li>
253+
<li><a href="configs/boxinst">BoxInst (CVPR'2021)</a></li>
243254
</ul>
244255
</td>
245256
<td>
@@ -319,6 +330,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
319330
<li><a href="configs/resnet_strikes_back">ResNet strikes back (ArXiv'2021)</a></li>
320331
<li><a href="configs/efficientnet">EfficientNet (ArXiv'2021)</a></li>
321332
<li><a href="configs/convnext">ConvNeXt (CVPR'2022)</a></li>
333+
<li><a href="projects/ConvNeXt-V2">ConvNeXtv2 (ArXiv'2023)</a></li>
322334
</ul>
323335
</td>
324336
<td>

‎README_zh-CN.md‎

Lines changed: 19 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -93,10 +93,14 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
9393
<img src="https://user-images.githubusercontent.com/12907710/208044554-1e8de6b5-48d8-44e4-a7b5-75076c7ebb71.png"/>
9494
</div>
9595

96-
**v3.0.0rc5** 版本已经在 2022.12.26 发布：
96+
**v3.0.0rc6** 版本已经在 2023.2.24 发布：
9797

98-
- 支持了 [RTMDet](https://arxiv.org/abs/2212.07784) 的实例分割模型。RTMDet 的技术报告发布在了 [arxiv](https://arxiv.org/abs/2212.07784) 上。
99-
- 支持了 [SSH: Single Stage Headless Face Detector](https://arxiv.org/abs/1708.03979) 论文中的 SSHContextModule
98+
- 支持了 [Boxinst](configs/boxinst), [Objects365 Dataset](configs/objects365) 和 [Separated and Occluded COCO metric](docs/zh_cn/user_guides/useful_tools.md#coco-分离和遮挡实例分割性能评估)
99+
- 在 `Projects` 中支持了 [ConvNeXt-V2](projects/ConvNeXt-V2), [DiffusionDet](projects/DiffusionDet) 和 [EfficientDet](projects/EfficientDet), [Detic](projects/Detic) 的推理
100+
- 重构了 [DETR](configs/detr) 系列并支持了 [Conditional-DETR](configs/conditional_detr), [DAB-DETR](configs/dab_detr) 和 [DINO](configs/dino)
101+
- 支持了通过 `DetInferencer` 用于推理, Test Time Augmentation 以及从注册表(registry)自动导入模块
102+
- 支持了 RTMDet-Ins 的 ONNXRuntime 和 TensorRT [部署](configs/rtmdet/README.md#deployment-tutorial)
103+
- 支持了检测器[计算 FLOPS](docs/zh_cn/user_guides/useful_tools.md#模型复杂度)
100104

101105
## 安装
102106

@@ -206,7 +210,13 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
206210
<li><a href="configs/deformable_detr">Deformable DETR (ICLR'2021)</a></li>
207211
<li><a href="configs/tood">TOOD (ICCV'2021)</a></li>
208212
<li><a href="configs/ddod">DDOD (ACM MM'2021)</a></li>
209-
<li><a href="configs/RTMDet">RTMDet (ArXiv'2022)</a></li>
213+
<li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li>
214+
<li><a href="configs/conditional_detr">Conditional DETR (ICCV'2021)</a></li>
215+
<li><a href="configs/dab_detr">DAB-DETR (ICLR'2022)</a></li>
216+
<li><a href="configs/dino">DINO (ICLR'2023)</a></li>
217+
<li><a href="projects/DiffusionDet">DiffusionDet (ArXiv'2023)</a></li>
218+
<li><a href="projects/EfficientDet">EfficientDet (CVPR'2020)</a></li>
219+
<li><a href="projects/Detic">Detic (ECCV'2022)</a></li>
210220
</ul>
211221
</td>
212222
<td>
@@ -224,9 +234,10 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
224234
<li><a href="configs/scnet">SCNet (AAAI'2021)</a></li>
225235
<li><a href="configs/queryinst">QueryInst (ICCV'2021)</a></li>
226236
<li><a href="configs/mask2former">Mask2Former (ArXiv'2021)</a></li>
227-
<li><a href="configs/condinst">CondInst (ECCV 2020)</a></li>
228-
<li><a href="projects/SparseInst">SparseInst (CVPR 2022)</a></li>
229-
<li><a href="configs/RTMDet">RTMDet (ArXiv'2022)</a></li>
237+
<li><a href="configs/condinst">CondInst (ECCV'2020)</a></li>
238+
<li><a href="projects/SparseInst">SparseInst (CVPR'2022)</a></li>
239+
<li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li>
240+
<li><a href="configs/boxinst">BoxInst (CVPR'2021)</a></li>
230241
</ul>
231242
</td>
232243
<td>
@@ -306,6 +317,7 @@ MMDetection 是一个基于 PyTorch 的目标检测开源工具箱。它是 [Ope
306317
<li><a href="configs/resnet_strikes_back">ResNet strikes back (ArXiv'2021)</a></li>
307318
<li><a href="configs/efficientnet">EfficientNet (ArXiv'2021)</a></li>
308319
<li><a href="configs/convnext">ConvNeXt (CVPR'2022)</a></li>
320+
<li><a href="projects/ConvNeXt-V2">ConvNeXtv2 (ArXiv'2023)</a></li>
309321
</ul>
310322
</td>
311323
<td>

‎docker/Dockerfile‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ RUN apt-get update \
2929

3030
# Install MMEngine and MMCV
3131
RUN pip install openmim && \
32-
mim install "mmengine==0.3.0" "mmcv>=2.0.0rc1"
32+
mim install "mmengine>=0.6.0" "mmcv>=2.0.0rc4"
3333

3434
# Install MMDetection
3535
RUN conda clean --all \

‎docker/serve/Dockerfile‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@ ARG CUDA="11.1"
33
ARG CUDNN="8"
44
FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
55

6-
ARG MMCV="2.0.0rc1"
7-
ARG MMDET="3.0.0rc5"
6+
ARG MMCV="2.0.0rc4"
7+
ARG MMDET="3.0.0rc6"
88

99
ENV PYTHONUNBUFFERED TRUE
1010

‎docker/serve_cn/Dockerfile‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@ ARG CUDA="11.1"
33
ARG CUDNN="8"
44
FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
55

6-
ARG MMCV="2.0.0rc1"
7-
ARG MMDET="3.0.0rc5"
6+
ARG MMCV="2.0.0rc4"
7+
ARG MMDET="3.0.0rc6"
88

99
ENV PYTHONUNBUFFERED TRUE
1010

‎docs/en/notes/changelog.md‎

Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,88 @@
11
# Changelog of v3.x
22

3+
## v3.0.0rc6 (24/2/2023)
4+
5+
### Highlights
6+
7+
- Support [Boxinst](../../../configs/boxinst), [Objects365 Dataset](../../../configs/objects365), and [Separated and Occluded COCO metric](../user_guides/useful_tools.md#COCO-Separated-&-Occluded-Mask-Metric)
8+
- Support [ConvNeXt-V2](../../../projects/ConvNeXt-V2), [DiffusionDet](../../../projects/DiffusionDet), and inference of [EfficientDet](../../../projects/EfficientDet) and [Detic](../../../projects/Detic) in `Projects`
9+
- Refactor [DETR](../../../configs/detr) series and support [Conditional-DETR](../../../configs/conditional_detr), [DAB-DETR](../../../configs/dab_detr), and [DINO](../../../configs/detr)
10+
- Support `DetInferencer` for inference, Test Time Augmentation, and automatically importing modules from registry
11+
- Support RTMDet-Ins ONNXRuntime and TensorRT [deployment](../../../configs/rtmdet/README.md#deployment-tutorial)
12+
- Support [calculating FLOPs of detectors](../user_guides/useful_tools.md#Model-Complexity)
13+
14+
### New Features
15+
16+
- Support [Boxinst](https://arxiv.org/abs/2012.02310) (#9525)
17+
- Support [Objects365 Dataset](https://openaccess.thecvf.com/content_ICCV_2019/papers/Shao_Objects365_A_Large-Scale_High-Quality_Dataset_for_Object_Detection_ICCV_2019_paper.pdf) (#9600)
18+
- Support [ConvNeXt-V2](http://arxiv.org/abs/2301.00808) in `Projects` (#9619)
19+
- Support [DiffusionDet](https://arxiv.org/abs/2211.09788) in `Projects` (#9639, #9768)
20+
- Support [Detic](http://arxiv.org/abs/2201.02605) inference in `Projects` (#9645)
21+
- Support [EfficientDet](https://arxiv.org/abs/1911.09070) inference in `Projects` (#9645)
22+
- Support [Separated and Occluded COCO metric](https://arxiv.org/abs/2210.10046) (#9710)
23+
- Support auto import modules from registry (#9143)
24+
- Refactor DETR series and support Conditional-DETR, DAB-DETR and DINO (#9646)
25+
- Support `DetInferencer` for inference (#9561)
26+
- Support Test Time Augmentation (#9452)
27+
- Support calculating FLOPs of detectors (#9777)
28+
29+
### Bug Fixes
30+
31+
- Fix deprecating old type alias due to new version of numpy (#9625, #9537)
32+
- Fix VOC metrics (#9784)
33+
- Fix the wrong link of RTMDet-x log (#9549)
34+
- Fix RTMDet link in README (#9575)
35+
- Fix MMDet get flops error (#9589)
36+
- Fix `use_depthwise` in RTMDet (#9624)
37+
- Fix `albumentations` augmentation post process with masks (#9551)
38+
- Fix DETR series Unit Test (#9647)
39+
- Fix `LoadPanopticAnnotations` bug (#9703)
40+
- Fix `isort` CI (#9680)
41+
- Fix amp pooling overflow (#9670)
42+
- Fix docstring about noise in DINO (#9747)
43+
- Fix potential bug in `MultiImageMixDataset` (#9764)
44+
45+
### Improvements
46+
47+
- Replace NumPy transpose with PyTorch permute to speed-up (#9762)
48+
- Deprecate `sklearn` (#9725)
49+
- Add RTMDet-Ins deployment guide (#9823)
50+
- Update RTMDet config and README (#9603)
51+
- Replace the models used in the tutorial document with RTMDet (#9843)
52+
- Adjust the minimum supported python version to 3.7 (#9602)
53+
- Support modifying palette through configuration (#9445)
54+
- Update README document in `Project` (#9599)
55+
- Replace `github` with `gitee` in `.pre-commit-config-zh-cn.yaml` file (#9586)
56+
- Use official `isort` in `.pre-commit-config.yaml` file (#9701)
57+
- Change MMCV minimum version to `2.0.0rc4` for `dev-3.x` (#9695)
58+
- Add Chinese version of single_stage_as_rpn.md and test_results_submission.md (#9434)
59+
- Add OpenDataLab download link (#9605, #9738)
60+
- Add type hints of several layers (#9346)
61+
- Add typehint for `DarknetBottleneck` (#9591)
62+
- Add dockerfile (#9659)
63+
- Add twitter, discord, medium, and youtube link (#9775)
64+
- Prepare for merging refactor-detr (#9656)
65+
- Add metafile to ConditionalDETR, DABDETR and DINO (#9715)
66+
- Support to modify `non_blocking` parameters (#9723)
67+
- Comment repeater visualizer register (#9740)
68+
- Update user guide: `finetune.md` and `inference.md` (#9578)
69+
70+
### New Contributors
71+
72+
- @NoFish-528 made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9346>
73+
- @137208 made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9434>
74+
- @lyviva made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9625>
75+
- @zwhus made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9589>
76+
- @zylo117 made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9670>
77+
- @chg0901 made their first contribution in <https://github.com/open-mmlab/mmdetection/pull/9740>
78+
- @DanShouzhu made their first contribution in https://github.com/open-mmlab/mmdetection/pull/9578
79+
80+
### Contributors
81+
82+
A total of 27 developers contributed to this release.
83+
84+
Thanks @JosonChan1998, @RangeKing, @NoFish-528, @likyoo, @Xiangxu-0103, @137208, @PeterH0323, @tianleiSHI, @wufan-tb, @lyviva, @zwhus, @jshilong, @Li-Qingyun, @sanbuphy, @zylo117, @triple-Mu, @KeiChiTse, @LYMDLUT, @nijkah, @chg0901, @DanShouzhu, @zytx121, @vansin, @BIGWangYuDong, @hhaAndroid, @RangiLyu, @ZwwWayne
85+
386
## v3.0.0rc5 (26/12/2022)
487

588
### Highlights
@@ -25,6 +108,7 @@
25108
- Fix demo API in instance segmentation tutorial (#9226)
26109
- Fix `analyze_results` (#9380)
27110
- Fix the error that Readthedocs API cannot be displayed (#9510)
111+
- Fix the error when there are no prediction results and support visualize the groundtruth of TTA (#9840)
28112

29113
### Improvements
30114

‎docs/en/notes/faq.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,8 +10,8 @@ We list some common troubles faced by many users and their corresponding solutio
1010

1111
| MMDetection version | MMCV version | MMEngine version |
1212
| :-----------------: | :---------------------: | :----------------------: |
13-
| 3.x | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.4.0, \<1.0.0 |
14-
| 3.0.0rc6 | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
13+
| 3.x | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.6.0, \<1.0.0 |
14+
| 3.0.0rc6 | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.6.0, \<1.0.0 |
1515
| 3.0.0rc5 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
1616
| 3.0.0rc4 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
1717
| 3.0.0rc3 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |

‎docs/zh_cn/notes/faq.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,8 +10,8 @@
1010

1111
| MMDetection 版本 | MMCV 版本 | MMEngine 版本 |
1212
| :--------------: | :---------------------: | :----------------------: |
13-
| 3.x | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.4.0, \<1.0.0 |
14-
| 3.0.0rc6 | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
13+
| 3.x | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.6.0, \<1.0.0 |
14+
| 3.0.0rc6 | mmcv>=2.0.0rc4, \<2.1.0 | mmengine>=0.6.0, \<1.0.0 |
1515
| 3.0.0rc5 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
1616
| 3.0.0rc4 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |
1717
| 3.0.0rc3 | mmcv>=2.0.0rc1, \<2.1.0 | mmengine>=0.3.0, \<1.0.0 |

‎mmdet/__init__.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@
99
mmcv_maximum_version = '2.1.0'
1010
mmcv_version = digit_version(mmcv.__version__)
1111

12-
mmengine_minimum_version = '0.4.0'
12+
mmengine_minimum_version = '0.6.0'
1313
mmengine_maximum_version = '1.0.0'
1414
mmengine_version = digit_version(mmengine.__version__)
1515

0 commit comments

Comments
 (0)