Bump version to 0.6.0

Bump version to 0.6.0

Author: hhaAndroid

.circleci/test.yml

@@ -67,7 +67,7 @@ jobs:
           command: |
             pip install -U openmim
             mim install git+https://github.com/open-mmlab/mmengine.git@main
-            mim install 'mmcv >= 2.0.0rc4'
+            mim install 'mmcv >= 2.0.0'
             mim install git+https://github.com/open-mmlab/mmdetection.git@dev-3.x
             pip install -r requirements/albu.txt
             pip install -r requirements/tests.txt
@@ -90,16 +90,17 @@ jobs:
           name: Run unittests
           command: |
             export LD_LIBRARY_PATH=/home/circleci/project/onnxruntime-linux-x64-1.8.1/lib:${LD_LIBRARY_PATH}
-            coverage run --branch --source mmyolo -m pytest tests/
-            coverage xml
-            coverage report -m
+            pytest tests/
+#            coverage run --branch --source mmyolo -m pytest tests/
+#            coverage xml
+#            coverage report -m
   build_cuda:
     parameters:
       torch:
         type: string
       cuda:
         type: enum
-        enum: ["10.1", "10.2", "11.1", "11.0"]
+        enum: ["10.1", "10.2", "11.0", "11.7"]
       cudnn:
         type: integer
         default: 7
@@ -125,7 +126,7 @@ jobs:
           command: |
             docker exec mmyolo pip install -U openmim
             docker exec mmyolo mim install -e /mmengine
-            docker exec mmyolo mim install 'mmcv >= 2.0.0rc4'
+            docker exec mmyolo mim install 'mmcv >= 2.0.0'
             docker exec mmyolo pip install -e /mmdetection
             docker exec mmyolo pip install -r requirements/albu.txt
             docker exec mmyolo pip install -r requirements/tests.txt
@@ -168,6 +169,9 @@ workflows:
             - lint
       - build_cpu:
           name: maximum_version_cpu
+          # mmdeploy not supported
+#          torch: 2.0.0
+#          torchvision: 0.15.1
           torch: 1.12.1
           torchvision: 0.13.1
           python: 3.9.0
@@ -185,6 +189,13 @@ workflows:
           cuda: "10.2"
           requires:
             - hold
+      - build_cuda:
+          name: maximum_version_gpu
+          torch: 2.0.0
+          cuda: "11.7"
+          cudnn: 8
+          requires:
+            - hold
   merge_stage_test:
     when:
       not: << pipeline.parameters.lint_only >>

.dev_scripts/gather_models.py

@@ -108,6 +108,7 @@ def get_dataset_name(config):
     name_map = dict(
         CityscapesDataset='Cityscapes',
         CocoDataset='COCO',
+        PoseCocoDataset='COCO Person',
         YOLOv5CocoDataset='COCO',
         CocoPanopticDataset='COCO',
         YOLOv5DOTADataset='DOTA 1.0',

README.md

@@ -77,17 +77,13 @@ English | [简体中文](README_zh-CN.md)
 
 ## 🥳 🚀 What's New [🔝](#-table-of-contents)
 
-💎 **v0.5.0** was released on 2/3/2023:
-
-1. Support [RTMDet-R](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/README.md#rotated-object-detection) rotated object detection
-2. Support for using mask annotation to improve [YOLOv8](https://github.com/open-mmlab/mmyolo/blob/dev/configs/yolov8/README.md) object detection performance
-3. Support [MMRazor](https://github.com/open-mmlab/mmyolo/blob/dev/configs/razor/subnets/README.md) searchable NAS sub-network as the backbone of YOLO series algorithm
-4. Support calling [MMRazor](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/distillation/README.md) to distill the knowledge of RTMDet
-5. [MMYOLO](https://mmyolo.readthedocs.io/zh_CN/dev/) document structure optimization, comprehensive content upgrade
-6. Improve YOLOX mAP and training speed based on RTMDet training hyperparameters
-7. Support calculation of model parameters and FLOPs, provide GPU latency data on T4 devices, and update [Model Zoo](https://github.com/open-mmlab/mmyolo/blob/dev/docs/en/model_zoo.md)
-8. Support test-time augmentation (TTA)
-9. Support RTMDet, YOLOv8 and YOLOv7 assigner visualization
+💎 **v0.6.0** was released on 15/8/2023:
+
+- Support YOLOv5 instance segmentation
+- Support YOLOX-Pose based on MMPose
+- Add 15 minutes instance segmentation tutorial.
+- YOLOv5 supports using mask annotation to optimize bbox
+- Add Multi-scale training and testing docs
 
 For release history and update details, please refer to [changelog](https://mmyolo.readthedocs.io/en/latest/notes/changelog.html).
 
@@ -150,7 +146,7 @@ conda activate mmyolo
 pip install openmim
 mim install "mmengine>=0.6.0"
 mim install "mmcv>=2.0.0rc4,<2.1.0"
-mim install "mmdet>=3.0.0rc6,<3.1.0"
+mim install "mmdet>=3.0.0,<4.0.0"
 git clone https://github.com/open-mmlab/mmyolo.git
 cd mmyolo
 # Install albumentations
@@ -184,6 +180,7 @@ For different parts from MMDetection, we have also prepared user guides and adva
 <summary>Recommended Topics</summary>
 
 - [How to contribute code to MMYOLO](docs/en/recommended_topics/contributing.md)
+- [Training testing tricks](docs/en/recommended_topics/training_testing_tricks.md)
 - [MMYOLO model design](docs/en/recommended_topics/model_design.md)
 - [Algorithm principles and implementation](docs/en/recommended_topics/algorithm_descriptions/)
 - [Replace the backbone network](docs/en/recommended_topics/replace_backbone.md)
@@ -192,7 +189,7 @@ For different parts from MMDetection, we have also prepared user guides and adva
 - [Visualization](docs/en/recommended_topics/visualization.md)
 - [Model deployment](docs/en/recommended_topics/deploy/)
 - [Troubleshooting steps](docs/en/recommended_topics/troubleshooting_steps.md)
-- [MMYOLO industry examples](docs/en/recommended_topics/industry_examples.md)
+- [MMYOLO application examples](docs/en/recommended_topics/application_examples/)
 - [MM series repo essential basics](docs/en/recommended_topics/mm_basics.md)
 - [Dataset preparation and description](docs/en/recommended_topics/dataset_preparation.md)
 
@@ -204,6 +201,7 @@ For different parts from MMDetection, we have also prepared user guides and adva
 - [Resume training](docs/en/common_usage/resume_training.md)
 - [Enabling and disabling SyncBatchNorm](docs/en/common_usage/syncbn.md)
 - [Enabling AMP](docs/en/common_usage/amp_training.md)
+- [Multi-scale training and testing](docs/en/common_usage/ms_training_testing.md)
 - [TTA Related Notes](docs/en/common_usage/tta.md)
 - [Add plugins to the backbone network](docs/en/common_usage/plugins.md)
 - [Freeze layers](docs/en/common_usage/freeze_layers.md)
@@ -283,6 +281,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md).
 <summary><b>Supported Algorithms</b></summary>
 
 - [x] [YOLOv5](configs/yolov5)
+- [ ] [YOLOv5u](configs/yolov5/yolov5u) (Inference only)
 - [x] [YOLOX](configs/yolox)
 - [x] [RTMDet](configs/rtmdet)
 - [x] [RTMDet-Rotated](configs/rtmdet)
@@ -405,8 +404,8 @@ This project is released under the [GPL 3.0 license](LICENSE).
 
 - [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab foundational library for training deep learning models.
 - [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab foundational library for computer vision.
-- [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages.
-- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab image classification toolbox and benchmark.
+- [MMPreTrain](https://github.com/open-mmlab/mmpretrain): OpenMMLab pre-training toolbox and benchmark.
+- [MMagic](https://github.com/open-mmlab/mmagic): Open**MM**Lab **A**dvanced, **G**enerative and **I**ntelligent **C**reation toolbox.
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
@@ -424,4 +423,6 @@ This project is released under the [GPL 3.0 license](LICENSE).
 - [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
 - [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.
 - [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework.
+- [MIM](https://github.com/open-mmlab/mim): MIM installs OpenMMLab packages.
 - [MMEval](https://github.com/open-mmlab/mmeval): OpenMMLab machine learning evaluation library.
+- [Playground](https://github.com/open-mmlab/playground): A central hub for gathering and showcasing amazing projects built upon OpenMMLab.

README_zh-CN.md

@@ -78,17 +78,13 @@
 
 ## 🥳 🚀 最新进展 [🔝](#-table-of-contents)
 
-💎 **v0.5.0** 版本已经在 2023.3.2 发布：
-
-1. 支持了 [RTMDet-R](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/README.md#rotated-object-detection) 旋转框目标检测任务和算法
-2. [YOLOv8](https://github.com/open-mmlab/mmyolo/blob/dev/configs/yolov8/README.md) 支持使用 mask 标注提升目标检测模型性能
-3. 支持 [MMRazor](https://github.com/open-mmlab/mmyolo/blob/dev/configs/razor/subnets/README.md) 搜索的 NAS 子网络作为 YOLO 系列算法的 backbone
-4. 支持调用 [MMRazor](https://github.com/open-mmlab/mmyolo/blob/dev/configs/rtmdet/distillation/README.md) 对 RTMDet 进行知识蒸馏
-5. [MMYOLO](https://mmyolo.readthedocs.io/zh_CN/dev/) 文档结构优化，内容全面升级
-6. 基于 RTMDet 训练超参提升 YOLOX 精度和训练速度
-7. 支持模型参数量、FLOPs 计算和提供 T4 设备上 GPU 延时数据，并更新了 [Model Zoo](https://github.com/open-mmlab/mmyolo/blob/dev/docs/zh_cn/model_zoo.md)
-8. 支持测试时增强 TTA
-9. 支持 RTMDet、YOLOv8 和 YOLOv7 assigner 可视化
+💎 **v0.6.0** 版本已经在 2023.8.15 发布：
+
+- 支持 YOLOv5 实例分割
+- 基于 MMPose 支持 YOLOX-Pose
+- 添加 15 分钟的实例分割教程
+- YOLOv5 支持使用 mask 标注来优化边界框
+- 添加多尺度训练和测试文档
 
 我们提供了实用的**脚本命令速查表**
 
@@ -108,7 +104,7 @@
 | 🌟  | 自定义数据集从标注到部署保姆级教程 | [![Link](https://i2.hdslb.com/bfs/archive/13f566c89a18c9c881713b63ec14da952d4c0b14.jpg@112w_63h_1c.webp)](https://www.bilibili.com/video/BV1RG4y137i5)  [![bilibili](https://img.shields.io/badge/dynamic/json?label=views&style=social&logo=bilibili&query=data.stat.view&url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1RG4y137i5)](https://www.bilibili.com/video/BV1JG4y1d7GC) |                                                 [自定义数据集从标注到部署保姆级教程](https://github.com/open-mmlab/mmyolo/blob/dev/docs/zh_cn/user_guides/custom_dataset.md)                                                  |
 | 🌟  |      顶会第一步 · 模块自定义       | [![Link](http://i2.hdslb.com/bfs/archive/5b23d41ac57466824eaf185ef806ef734414e93b.jpg@112w_63h_1c.webp)](https://www.bilibili.com/video/BV1yd4y1j7VD)  [![bilibili](https://img.shields.io/badge/dynamic/json?label=views&style=social&logo=bilibili&query=data.stat.view&url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1yd4y1j7VD)](https://www.bilibili.com/video/BV1yd4y1j7VD)  |                                    [顶会第一步·模块自定义.ipynb](https://github.com/open-mmlab/OpenMMLabCourse/blob/main/codes/MMYOLO_tutorials/[实用类第四期]顶会第一步·模块自定义.ipynb)                                    |
 
-完整视频列表请参考 [资源汇总页面](https://mmyolo.readthedocs.io/zh_CN/latest/article.html)
+完整视频列表请参考 [中文解读资源汇总 - 视频](https://mmyolo.readthedocs.io/zh_CN/latest/get_started/article.html)
 
 发布历史和更新细节请参考 [更新日志](https://mmyolo.readthedocs.io/zh_CN/latest/notes/changelog.html)
 
@@ -171,7 +167,7 @@ conda activate mmyolo
 pip install openmim
 mim install "mmengine>=0.6.0"
 mim install "mmcv>=2.0.0rc4,<2.1.0"
-mim install "mmdet>=3.0.0rc6,<3.1.0"
+mim install "mmdet>=3.0.0,<4.0.0"
 git clone https://github.com/open-mmlab/mmyolo.git
 cd mmyolo
 # Install albumentations
@@ -205,6 +201,7 @@ MMYOLO 用法和 MMDetection 几乎一致，所有教程都是通用的，你也
 <summary>推荐专题</summary>
 
 - [如何给 MMYOLO 贡献代码](docs/zh_cn/recommended_topics/contributing.md)
+- [训练和测试技巧](docs/zh_cn/recommended_topics/training_testing_tricks.md)
 - [MMYOLO 模型结构设计](docs/zh_cn/recommended_topics/model_design.md)
 - [原理和实现全解析](docs/zh_cn/recommended_topics/algorithm_descriptions/)
 - [轻松更换主干网络](docs/zh_cn/recommended_topics/replace_backbone.md)
@@ -213,7 +210,7 @@ MMYOLO 用法和 MMDetection 几乎一致，所有教程都是通用的，你也
 - [关于可视化的一切](docs/zh_cn/recommended_topics/visualization.md)
 - [模型部署流程](docs/zh_cn/recommended_topics/deploy/)
 - [常见错误排查步骤](docs/zh_cn/recommended_topics/troubleshooting_steps.md)
-- [MMYOLO 产业范例介绍](docs/zh_cn/recommended_topics/industry_examples.md)
+- [MMYOLO 应用范例介绍](docs/zh_cn/recommended_topics/application_examples/)
 - [MM 系列 Repo 必备基础](docs/zh_cn/recommended_topics/mm_basics.md)
 - [数据集准备和说明](docs/zh_cn/recommended_topics/dataset_preparation.md)
 
@@ -225,9 +222,10 @@ MMYOLO 用法和 MMDetection 几乎一致，所有教程都是通用的，你也
 - [恢复训练](docs/zh_cn/common_usage/resume_training.md)
 - [开启和关闭 SyncBatchNorm](docs/zh_cn/common_usage/syncbn.md)
 - [开启混合精度训练](docs/zh_cn/common_usage/amp_training.md)
+- [多尺度训练和测试](docs/zh_cn/common_usage/ms_training_testing.md)
 - [测试时增强相关说明](docs/zh_cn/common_usage/tta.md)
 - [给主干网络增加插件](docs/zh_cn/common_usage/plugins.md)
-- [冻结指定网络层权重](docs/zh_cn/common_usage/common_usage/freeze_layers.md)
+- [冻结指定网络层权重](docs/zh_cn/common_usage/freeze_layers.md)
 - [输出模型预测结果](docs/zh_cn/common_usage/output_predictions.md)
 - [设置随机种子](docs/zh_cn/common_usage/set_random_seed.md)
 - [算法组合替换教程](docs/zh_cn/common_usage/module_combination.md)
@@ -305,6 +303,7 @@ MMYOLO 用法和 MMDetection 几乎一致，所有教程都是通用的，你也
 <summary><b>支持的算法</b></summary>
 
 - [x] [YOLOv5](configs/yolov5)
+- [ ] [YOLOv5u](configs/yolov5/yolov5u) (仅推理)
 - [x] [YOLOX](configs/yolox)
 - [x] [RTMDet](configs/rtmdet)
 - [x] [RTMDet-Rotated](configs/rtmdet)
@@ -426,8 +425,8 @@ MMYOLO 是一款由来自不同高校和企业的研发人员共同参与贡献
 
 - [MMEngine](https://github.com/open-mmlab/mmengine): OpenMMLab 深度学习模型训练基础库
 - [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
-- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
-- [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
+- [MMPreTrain](https://github.com/open-mmlab/mmpretrain): OpenMMLab 深度学习预训练工具箱
+- [MMagic](https://github.com/open-mmlab/mmagic): OpenMMLab 新一代人工智能内容生成（AIGC）工具箱
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
@@ -445,7 +444,9 @@ MMYOLO 是一款由来自不同高校和企业的研发人员共同参与贡献
 - [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
 - [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 图片视频生成模型工具箱
 - [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架
+- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
 - [MMEval](https://github.com/open-mmlab/mmeval): OpenMMLab 机器学习算法评测库
+- [Playground](https://github.com/open-mmlab/playground): 收集和展示 OpenMMLab 相关的前沿、有趣的社区项目
 
 ## ❤️ 欢迎加入 OpenMMLab 社区 [🔝](#-table-of-contents)
 

configs/_base_/default_runtime.py

@@ -25,10 +25,19 @@
 load_from = None
 resume = False
 
-# file_client_args = dict(
-#         backend='petrel',
-#         path_mapping=dict({
-#             './data/': 's3://openmmlab/datasets/detection/',
-#             'data/': 's3://openmmlab/datasets/detection/'
-#         }))
-file_client_args = dict(backend='disk')
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions
+# before MMDet 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+
+backend_args = None

configs/_base_/det_p5_tta.py

@@ -1,11 +1,12 @@
-# TODO: Need to solve the problem of multiple file_client_args parameters
-# _file_client_args = dict(
+# TODO: Need to solve the problem of multiple backend_args parameters
+# _backend_args = dict(
 #     backend='petrel',
 #     path_mapping=dict({
 #         './data/': 's3://openmmlab/datasets/detection/',
 #         'data/': 's3://openmmlab/datasets/detection/'
 #     }))
-_file_client_args = dict(backend='disk')
+
+_backend_args = None
 
 tta_model = dict(
     type='mmdet.DetTTAModel',
@@ -37,7 +38,7 @@
 ]
 
 tta_pipeline = [
-    dict(type='LoadImageFromFile', file_client_args=_file_client_args),
+    dict(type='LoadImageFromFile', backend_args=_backend_args),
     dict(
         type='TestTimeAug',
         transforms=[