Merge branch 'dev-1.x' of github.com:open-mmlab/mmsegmentation into 1.x

Author: MeowZheng

.dev/batch_test_list.py

@@ -2,129 +2,129 @@
 # Inference Speed is tested on NVIDIA V100
 hrnet = [
     dict(
-        config='configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py',
+        config='configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py',
         checkpoint='fcn_hr18s_512x512_160k_ade20k_20200614_214413-870f65ac.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=33.0),
     ),
     dict(
-        config='configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py',
+        config='configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py',
         checkpoint='fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=76.31),
     ),
     dict(
-        config='configs/hrnet/fcn_hr48_512x512_160k_ade20k.py',
+        config='configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py',
         checkpoint='fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth',
         eval='mIoU',
         metric=dict(mIoU=42.02),
     ),
     dict(
-        config='configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py',
+        config='configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py',
         checkpoint='fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=80.65),
     ),
 ]
 pspnet = [
     dict(
-        config='configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py',
+        config='configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py',
         checkpoint='pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=78.55),
     ),
     dict(
-        config='configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py',
+        config='configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py',
         checkpoint='pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=79.76),
     ),
     dict(
-        config='configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py',
+        config='configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py',
         checkpoint='pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=44.39),
     ),
     dict(
-        config='configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py',
+        config='configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py',
         checkpoint='pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=42.48),
     ),
 ]
 resnest = [
     dict(
-        config='configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py',
+        config='configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py', # noqa
         checkpoint='pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=45.44),
     ),
     dict(
-        config='configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py',
+        config='configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py', # noqa
         checkpoint='pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=78.57),
     ),
 ]
 fastscnn = [
     dict(
-        config='configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py',
+        config='configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py',
         checkpoint='fast_scnn_8x4_160k_lr0.12_cityscapes-0cec9937.pth',
         eval='mIoU',
         metric=dict(mIoU=70.96),
     )
 ]
 deeplabv3plus = [
     dict(
-        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py', # noqa
+        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py', # noqa
         checkpoint='deeplabv3plus_r101-d8_769x769_80k_cityscapes_20200607_000405-a7573d20.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=80.98),
     ),
     dict(
-        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py', # noqa
+        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py', # noqa
         checkpoint='deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=80.97),
     ),
     dict(
-        config='configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py', # noqa
+        config='configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py', # noqa
         checkpoint='deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=80.09),
     ),
     dict(
-        config='configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py', # noqa
+        config='configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py', # noqa
         checkpoint='deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=79.83),
     ),
 ]
 vit = [
     dict(
-        config='configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py',
+        config='configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py', # noqa
         checkpoint='upernet_vit-b16_ln_mln_512x512_160k_ade20k-f444c077.pth',
         eval='mIoU',
         metric=dict(mIoU=47.73),
     ),
     dict(
-        config='configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py',
+        config='configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py', # noqa
         checkpoint='upernet_deit-s16_ln_mln_512x512_160k_ade20k-c0cd652f.pth',
         eval='mIoU',
         metric=dict(mIoU=43.52),
     ),
 ]
 fp16 = [
     dict(
-        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes.py', # noqa
+        config='configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py', # noqa
         checkpoint='deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes_20200717_230920-f1104f4b.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=80.46),
     )
 ]
 swin = [
     dict(
-        config='configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py', # noqa
+        config='configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py', # noqa
         checkpoint='upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth', # noqa
         eval='mIoU',
         metric=dict(mIoU=44.41),

.dev/batch_train_list.txt

@@ -1,19 +1,19 @@
-configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py
-configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py
-configs/hrnet/fcn_hr48_512x512_160k_ade20k.py
-configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py
-configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py
-configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py
-configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py
-configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py
-configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py
-configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py
-configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py
-configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py
-configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py
-configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py
-configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py
-configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py
-configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py
-configs/deeplabv3plus/deeplabv3plus_r101-d8_fp16_512x1024_80k_cityscapes.py
-configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py
+configs/hrnet/fcn_hr18s_4xb4-160k_ade20k-512x512.py
+configs/hrnet/fcn_hr18s_4xb2-160k_cityscapes-512x1024.py
+configs/hrnet/fcn_hr48_4xb4-160k_ade20k-512x512.py
+configs/hrnet/fcn_hr48_4xb2-160k_cityscapes-512x1024.py
+configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py
+configs/pspnet/pspnet_r101-d8_4xb2-80k_cityscapes-512x1024.py
+configs/pspnet/pspnet_r101-d8_4xb4-160k_ade20k-512x512.py
+configs/pspnet/pspnet_r50-d8_4xb4-160k_ade20k-512x512.py
+configs/resnest/resnest_s101-d8_pspnet_4xb4-160k_ade20k-512x512.py
+configs/resnest/resnest_s101-d8_pspnet_4xb2-80k_cityscapes512x1024.py
+configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py
+configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-769x769.py
+configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-80k_cityscapes-512x1024.py
+configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py
+configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-769x769.py
+configs/vit/vit_vit-b16-ln_mln_upernet_8xb2-160k_ade20k-512x512.py
+configs/vit/vit_deit-s16-ln_mln_upernet_512x512_160k_ade20k-512x512.py
+configs/deeplabv3plus/deeplabv3plus_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
+configs/swin/swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py

README.md

@@ -17,8 +17,6 @@
     </sup>
   </div>
   <div>&nbsp;</div>
-</div>
-<br />
 
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/mmsegmentation)](https://pypi.org/project/mmsegmentation/)
 [![PyPI](https://img.shields.io/pypi/v/mmsegmentation)](https://pypi.org/project/mmsegmentation)
@@ -33,6 +31,22 @@ Documentation: <https://mmsegmentation.readthedocs.io/en/1.x/>
 
 English | [简体中文](README_zh-CN.md)
 
+</div>
+
+<div align="center">
+  <a href="https://openmmlab.medium.com/" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218352562-cdded397-b0f3-4ca1-b8dd-a60df8dca75b.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://discord.gg/raweFPmdzG" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a>
+  <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" />
+  <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;">
+    <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a>
+</div>
+
 ## Introduction
 
 MMSegmentation is an open source semantic segmentation toolbox based on PyTorch.
@@ -62,11 +76,11 @@ The 1.x branch works with **PyTorch 1.6+**.
 
 ## What's New
 
-v1.0.0rc5 was released on 01/02/2023.
+v1.0.0rc6 was released on 03/03/2023.
 Please refer to [changelog.md](docs/en/notes/changelog.md) for details and release history.
 
-- Support ISNet (ICCV'2021) in projects ([#2400](https://github.com/open-mmlab/mmsegmentation/pull/2400))
-- Support HSSN (CVPR'2022) in projects ([#2444](https://github.com/open-mmlab/mmsegmentation/pull/2444))
+- Support MMSegInferencer ([#2413](https://github.com/open-mmlab/mmsegmentation/pull/2413), [#2658](https://github.com/open-mmlab/mmsegmentation/pull/2658))
+- Support REFUGE dataset ([#2554](https://github.com/open-mmlab/mmsegmentation/pull/2554))
 
 ## Installation
 
@@ -81,13 +95,14 @@ There are also [advanced tutorials](https://mmsegmentation.readthedocs.io/en/dev
 
 A Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/1.x/demo/MMSegmentation_Tutorial.ipynb) on Colab.
 
-To migrate from MMSegmentation 1.x, please refer to [migration](docs/en/migration.md).
+To migrate from MMSegmentation 1.x, please refer to [migration](docs/en/migration).
 
 ## Benchmark and model zoo
 
 Results and models are available in the [model zoo](docs/en/model_zoo.md).
 
-Supported backbones:
+<details open>
+<summary>Supported backbones:</summary>
 
 - [x] ResNet (CVPR'2016)
 - [x] ResNeXt (CVPR'2017)
@@ -103,7 +118,10 @@ Supported backbones:
 - [x] [MAE (CVPR'2022)](configs/mae)
 - [x] [PoolFormer (CVPR'2022)](configs/poolformer)
 
-Supported methods:
+</details>
+
+<details open>
+<summary>Supported methods:</summary>
 
 - [x] [FCN (CVPR'2015/TPAMI'2017)](configs/fcn)
 - [x] [ERFNet (T-ITS'2017)](configs/erfnet)
@@ -142,7 +160,10 @@ Supported methods:
 - [x] [MaskFormer (NeurIPS'2021)](configs/maskformer)
 - [x] [Mask2Former (CVPR'2022)](configs/mask2former)
 
-Supported datasets:
+</details>
+
+<details open>
+<summary>Supported datasets:</summary>
 
 - [x] [Cityscapes](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#cityscapes)
 - [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#pascal-voc)
@@ -161,8 +182,14 @@ Supported datasets:
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/2_dataset_prepare.md#isaid)
 
+</details>
+
 Please refer to [FAQ](docs/en/notes/faq.md) for frequently asked questions.
 
+## Projects
+
+[Here](projects/README.md) are some implementations of SOTA models and solutions built on MMSegmentation, which are supported and maintained by community users. These projects demonstrate the best practices based on MMSegmentation for research and product development. We welcome and appreciate all the contributions to OpenMMLab ecosystem.
+
 ## Contributing
 
 We appreciate all contributions to improve MMSegmentation. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
@@ -191,7 +218,7 @@ If you find this project useful in your research, please consider cite:
 
 This project is released under the [Apache 2.0 license](LICENSE).
 
-## Projects in OpenMMLab
+## OpenMMLab Family
 
 - [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.

README_zh-CN.md

@@ -61,7 +61,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 
 ## 更新日志
 
-最新版本 v1.0.0rc5 在 2023.02.01 发布。
+最新版本 v1.0.0rc6 在 2023.03.03 发布。
 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/en/notes/changelog.md)。
 
 ## 安装
@@ -82,7 +82,8 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 
 测试结果和模型可以在[模型库](docs/zh_cn/model_zoo.md)中找到。
 
-已支持的骨干网络：
+<details open>
+<summary>已支持的骨干网络：</summary>
 
 - [x] ResNet (CVPR'2016)
 - [x] ResNeXt (CVPR'2017)
@@ -98,7 +99,10 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [MAE (CVPR'2022)](configs/mae)
 - [x] [PoolFormer (CVPR'2022)](configs/poolformer)
 
-已支持的算法：
+</details>
+
+<details open>
+<summary>已支持的算法：</summary>
 
 - [x] [FCN (CVPR'2015/TPAMI'2017)](configs/fcn)
 - [x] [ERFNet (T-ITS'2017)](configs/erfnet)
@@ -137,7 +141,10 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [MaskFormer (NeurIPS'2021)](configs/maskformer)
 - [x] [Mask2Former (CVPR'2022)](configs/mask2former)
 
-已支持的数据集：
+</details>
+
+<details open>
+<summary>已支持的数据集：</summary>
 
 - [x] [Cityscapes](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#cityscapes)
 - [x] [PASCAL VOC](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#pascal-voc)
@@ -156,15 +163,22 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
 - [x] [Vaihingen](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isprs-vaihingen)
 - [x] [iSAID](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/dataset_prepare.md#isaid)
 
+</details>
+
 如果遇到问题，请参考 [常见问题解答](docs/zh_cn/notes/faq.md)。
 
+## 社区项目
+
+[这里](projects/README.md)有一些由社区用户支持和维护的基于 MMSegmentation 的 SOTA 模型和解决方案的实现。这些项目展示了基于 MMSegmentation 的研究和产品开发的最佳实践。
+我们欢迎并感谢对 OpenMMLab 生态系统的所有贡献。
+
 ## 贡献指南
 
 我们感谢所有的贡献者为改进和提升 MMSegmentation 所作出的努力。请参考[贡献指南](.github/CONTRIBUTING.md)来了解参与项目贡献的相关指引。
 
 ## 致谢
 
-MMSegmentation 是一个由来自不同高校和企业的研发人员共同参与贡献的开源项目。我们感谢所有为项目提供算法复现和新功能支持的贡献者，以及提供宝贵反馈的用户。 我们希望这个工具箱和基准测试可以为社区提供灵活的代码工具，供用户复现已有算法并开发自己的新模型，从而不断为开源社区提供贡献。
+MMSegmentation 是一个由来自不同高校和企业的研发人员共同参与贡献的开源项目。我们感谢所有为项目提供算法复现和新功能支持的贡献者，以及提供宝贵反馈的用户。我们希望这个工具箱和基准测试可以为社区提供灵活的代码工具，供用户复现已有算法并开发自己的新模型，从而不断为开源社区提供贡献。
 
 ## 引用
 

configs/_base_/datasets/ade20k.py

@@ -25,7 +25,7 @@
 ]
 img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
 tta_pipeline = [
-    dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
+    dict(type='LoadImageFromFile', backend_args=None),
     dict(
         type='TestTimeAug',
         transforms=[

configs/_base_/datasets/ade20k_640x640.py

@@ -25,7 +25,7 @@
 ]
 img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
 tta_pipeline = [
-    dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
+    dict(type='LoadImageFromFile', backend_args=None),
     dict(
         type='TestTimeAug',
         transforms=[

configs/_base_/datasets/chase_db1.py

@@ -26,7 +26,7 @@
 ]
 img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
 tta_pipeline = [
-    dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
+    dict(type='LoadImageFromFile', backend_args=None),
     dict(
         type='TestTimeAug',
         transforms=[