Bump version to v0.19.0 (#623)

README.md

@@ -6,6 +6,8 @@
 [![Documentation Status](https://readthedocs.org/projects/mmclassification/badge/?version=latest)](https://mmclassification.readthedocs.io/en/latest/?badge=latest)
 [![codecov](https://codecov.io/gh/open-mmlab/mmclassification/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmclassification)
 [![license](https://img.shields.io/github/license/open-mmlab/mmclassification.svg)](https://github.com/open-mmlab/mmclassification/blob/master/LICENSE)
+[![PyPI](https://badge.fury.io/py/mmcls.svg)](https://pypi.org/project/mmcls/)
+[![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmclassification.svg)](https://github.com/open-mmlab/mmclassification/issues)
 
 ## Introduction
 
@@ -24,53 +26,62 @@ Documentation: https://mmclassification.readthedocs.io/en/latest/
 - Bag of training tricks
 - Large-scale training configs
 - High efficiency and extensibility
+- Powerful toolkits
 
 ## License
 
 This project is released under the [Apache 2.0 license](LICENSE).
 
 ## Changelog
 
+v0.19.0 was released in 31/12/2021.
+
+Highlights of the new version:
+- The **feature extraction** function has been enhanced. See [#593](https://github.com/open-mmlab/mmclassification/pull/593) for more details.
+- Provide the high-acc **ResNet-50** training settings from [*ResNet strikes back*](https://arxiv.org/abs/2110.00476).
+- Reproduce the training accuracy of **T2T-ViT** & **RegNetX**, and provide self-training checkpoints.
+- Support **DeiT** & **Conformer** backbone and checkpoints.
+- Provide a **CAM visualization** tool based on [pytorch-grad-cam](https://github.com/jacobgil/pytorch-grad-cam), and detailed [user guide](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#class-activation-map-visualization)!
+
 v0.18.0 was released in 30/11/2021.
 
 Highlights of the new version:
 - Support **MLP-Mixer** backbone and provide pre-trained checkpoints.
 - Add a tool to **visualize the learning rate curve** of the training phase. Welcome to use with the [tutorial](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#learning-rate-schedule-visualization)!
 
-v0.17.0 was released in 29/10/2021.
-
-Highlights of this version:
-- Support **Tokens-to-Token ViT** backbone and **Res2Net** backbone. Welcome to use!
-- Support **ImageNet21k** dataset.
-- Add a **pipeline visualization** tool. Try it with the [tutorials](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#pipeline-visualization)!
-
 Please refer to [changelog.md](docs/en/changelog.md) for more details and other release history.
 
 ## Benchmark and model zoo
 
 Results and models are available in the [model zoo](docs/en/model_zoo.md).
 
-Supported backbones:
-
-- [x] VGG
-- [x] ResNet
-- [x] ResNeXt
-- [x] SE-ResNet
-- [x] SE-ResNeXt
-- [x] RegNet
-- [x] ShuffleNetV1
-- [x] ShuffleNetV2
-- [x] MobileNetV2
-- [x] MobileNetV3
-- [x] Swin-Transformer
-- [x] RepVGG
-- [x] Vision-Transformer
-- [x] Transformer-in-Transformer
-- [x] Res2Net
-- [x] MLP-Mixer
-- [ ] DeiT
-- [ ] Conformer
+<details open>
+<summary>Supported backbones</summary>
+
+- [x] [VGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/vgg)
+- [x] [ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnet)
+- [x] [ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnext)
+- [x] [SE-ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
+- [x] [SE-ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
+- [x] [RegNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
+- [x] [ShuffleNetV1](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v1)
+- [x] [ShuffleNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v2)
+- [x] [MobileNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v2)
+- [x] [MobileNetV3](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v3)
+- [x] [Swin-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/swin_transformer)
+- [x] [RepVGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
+- [x] [Vision-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/vision_transformer)
+- [x] [Transformer-in-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/tnt)
+- [x] [Res2Net](https://github.com/open-mmlab/mmclassification/tree/master/configs/res2net)
+- [x] [MLP-Mixer](https://github.com/open-mmlab/mmclassification/tree/master/configs/mlp_mixer)
+- [x] [DeiT](https://github.com/open-mmlab/mmclassification/tree/master/configs/deit)
+- [x] [Conformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/conformer)
+- [x] [T2T-ViT](https://github.com/open-mmlab/mmclassification/tree/master/configs/t2t_vit)
 - [ ] EfficientNet
+- [ ] Twins
+- [ ] HRNet
+
+</details>
 
 ## Installation
 

README_zh-CN.md

@@ -8,6 +8,8 @@
 [![Documentation Status](https://readthedocs.org/projects/mmclassification/badge/?version=latest)](https://mmclassification.readthedocs.io/en/latest/?badge=latest)
 [![codecov](https://codecov.io/gh/open-mmlab/mmclassification/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmclassification)
 [![license](https://img.shields.io/github/license/open-mmlab/mmclassification.svg)](https://github.com/open-mmlab/mmclassification/blob/master/LICENSE)
+[![PyPI](https://badge.fury.io/py/mmcls.svg)](https://pypi.org/project/mmcls/)
+[![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmclassification.svg)](https://github.com/open-mmlab/mmclassification/issues)
 
 ## Introduction
 
@@ -23,53 +25,62 @@ MMClassification 是一款基于 PyTorch 的开源图像分类工具箱，是 [O
 - 支持配置多种训练技巧
 - 大量的训练配置文件
 - 高效率和高可扩展性
+- 功能强大的工具箱
 
 ## 许可证
 
 该项目开源自 [Apache 2.0 license](LICENSE).
 
 ## 更新日志
 
+2021/12/31 发布了 v0.19.0 版本
+
+新版本亮点：
+- **特征提取**功能得到了加强。详见 [#593](https://github.com/open-mmlab/mmclassification/pull/593)。
+- 提供了 **ResNet-50** 的高精度训练配置，原论文参见 [*ResNet strikes back*](https://arxiv.org/abs/2110.00476)。
+- 复现了 **T2T-ViT** 和 **RegNetX** 的训练精度，并提供了自训练的模型权重文件。
+- 支持了 **DeiT** 和 **Conformer** 主干网络，并提供了预训练模型。
+- 提供了一个 **CAM 可视化** 工具。该工具基于 [pytorch-grad-cam](https://github.com/jacobgil/pytorch-grad-cam)，我们提供了详细的 [使用教程](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#class-activation-map-visualization)！
+
 2021/11/30 发布了 v0.18.0 版本
 
-新版本的一些新功能如下：
+新版本亮点：
 - 支持了 **MLP-Mixer** 主干网络，欢迎使用！
 - 添加了一个**可视化学习率曲线**的工具，可以参考[教程](https://mmclassification.readthedocs.io/zh_CN/latest/tools/visualization.html#id3)使用
 
-2021/10/29 发布了 v0.17.0 版本
-
-该版本的一些新功能如下：
-- 支持了 **Tokens-to-Token ViT** 主干网络和 **Res2Net** 主干网络，欢迎使用！
-- 支持了 **ImageNet21k** 数据集
-- 添加了一个**可视化数据预处理**的工具，可以参考[教程](https://mmclassification.readthedocs.io/zh_CN/latest/tools/visualization.html#id2)使用
-
 发布历史和更新细节请参考 [更新日志](docs/en/changelog.md)
 
 ## 基准测试及模型库
 
 相关结果和模型可在 [model zoo](docs/en/model_zoo.md) 中获得
 
-支持的主干网络：
-
-- [x] VGG
-- [x] ResNet
-- [x] ResNeXt
-- [x] SE-ResNet
-- [x] SE-ResNeXt
-- [x] RegNet
-- [x] ShuffleNetV1
-- [x] ShuffleNetV2
-- [x] MobileNetV2
-- [x] MobileNetV3
-- [x] Swin-Transformer
-- [x] RepVGG
-- [x] Vision-Transformer
-- [x] Transformer-in-Transformer
-- [x] Res2Net
-- [x] MLP-Mixer
-- [ ] DeiT
-- [ ] Conformer
+<details open>
+<summary>支持的主干网络</summary>
+
+- [x] [VGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/vgg)
+- [x] [ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnet)
+- [x] [ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnext)
+- [x] [SE-ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
+- [x] [SE-ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
+- [x] [RegNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
+- [x] [ShuffleNetV1](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v1)
+- [x] [ShuffleNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v2)
+- [x] [MobileNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v2)
+- [x] [MobileNetV3](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v3)
+- [x] [Swin-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/swin_transformer)
+- [x] [RepVGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
+- [x] [Vision-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/vision_transformer)
+- [x] [Transformer-in-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/tnt)
+- [x] [Res2Net](https://github.com/open-mmlab/mmclassification/tree/master/configs/res2net)
+- [x] [MLP-Mixer](https://github.com/open-mmlab/mmclassification/tree/master/configs/mlp_mixer)
+- [x] [DeiT](https://github.com/open-mmlab/mmclassification/tree/master/configs/deit)
+- [x] [Conformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/conformer)
+- [x] [T2T-ViT](https://github.com/open-mmlab/mmclassification/tree/master/configs/t2t_vit)
 - [ ] EfficientNet
+- [ ] Twins
+- [ ] HRNet
+
+</details>
 
 ## 安装
 

docker/serve/Dockerfile

@@ -3,8 +3,8 @@ ARG CUDA="10.2"
 ARG CUDNN="7"
 FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
 
-ARG MMCV="1.3.16"
-ARG MMCLS="0.18.0"
+ARG MMCV="1.4.2"
+ARG MMCLS="0.19.0"
 
 ENV PYTHONUNBUFFERED TRUE
 

docs/en/changelog.md

@@ -1,5 +1,53 @@
 # Changelog
 
+## v0.19.0(31/12/2021)
+
+### Highlights
+
+- The feature extraction function has been enhanced. See [#593](https://github.com/open-mmlab/mmclassification/pull/593) for more details.
+- Provide the high-acc ResNet-50 training settings from [*ResNet strikes back*](https://arxiv.org/abs/2110.00476).
+- Reproduce the training accuracy of T2T-ViT & RegNetX, and provide self-training checkpoints.
+- Support DeiT & Conformer backbone and checkpoints.
+- Provide a CAM visualization tool based on [pytorch-grad-cam](https://github.com/jacobgil/pytorch-grad-cam), and detailed [user guide](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#class-activation-map-visualization)!
+
+### New Features
+
+- Support Precise BN. ([#401](https://github.com/open-mmlab/mmclassification/pull/401))
+- Add CAM visualization tool. ([#577](https://github.com/open-mmlab/mmclassification/pull/577))
+- Repeated Aug and Sampler Registry. ([#588](https://github.com/open-mmlab/mmclassification/pull/588))
+- Add DeiT backbone and checkpoints. ([#576](https://github.com/open-mmlab/mmclassification/pull/576))
+- Support LAMB optimizer. ([#591](https://github.com/open-mmlab/mmclassification/pull/591))
+- Implement the conformer backbone. ([#494](https://github.com/open-mmlab/mmclassification/pull/494))
+- Add the frozen function for Swin Transformer model. ([#574](https://github.com/open-mmlab/mmclassification/pull/574))
+- Support using checkpoint in Swin Transformer to save memory. ([#557](https://github.com/open-mmlab/mmclassification/pull/557))
+
+### Improvements
+
+- [Reproduction] Reproduce RegNetX training accuracy. ([#587](https://github.com/open-mmlab/mmclassification/pull/587))
+- [Reproduction] Reproduce training results of T2T-ViT. ([#610](https://github.com/open-mmlab/mmclassification/pull/610))
+- [Enhance] Provide high-acc training settings of ResNet. ([#572](https://github.com/open-mmlab/mmclassification/pull/572))
+- [Enhance] Set a random seed when the user does not set a seed. ([#554](https://github.com/open-mmlab/mmclassification/pull/554))
+- [Enhance] Added `NumClassCheckHook` and unit tests. ([#559](https://github.com/open-mmlab/mmclassification/pull/559))
+- [Enhance] Enhance feature extraction function. ([#593](https://github.com/open-mmlab/mmclassification/pull/593))
+- [Enhance] Improve efficiency of precision, recall, f1_score and support. ([#595](https://github.com/open-mmlab/mmclassification/pull/595))
+- [Enhance] Improve accuracy calculation performance. ([#592](https://github.com/open-mmlab/mmclassification/pull/592))
+- [Refactor] Refactor `analysis_log.py`. ([#529](https://github.com/open-mmlab/mmclassification/pull/529))
+- [Refactor] Use new API of matplotlib to handle blocking input in visualization. ([#568](https://github.com/open-mmlab/mmclassification/pull/568))
+- [CI] Cancel previous runs that are not completed. ([#583](https://github.com/open-mmlab/mmclassification/pull/583))
+- [CI] Skip build CI if only configs or docs modification. ([#575](https://github.com/open-mmlab/mmclassification/pull/575))
+
+### Bug Fixes
+
+- Fix test sampler bug. ([#611](https://github.com/open-mmlab/mmclassification/pull/611))
+- Try to create a symbolic link, otherwise copy. ([#580](https://github.com/open-mmlab/mmclassification/pull/580))
+- Fix a bug for multiple output in swin transformer. ([#571](https://github.com/open-mmlab/mmclassification/pull/571))
+
+### Docs Update
+
+- Update mmcv, torch, cuda version in Dockerfile and docs. ([#594](https://github.com/open-mmlab/mmclassification/pull/594))
+- Add analysis&misc docs. ([#525](https://github.com/open-mmlab/mmclassification/pull/525))
+- Fix docs build dependency. ([#584](https://github.com/open-mmlab/mmclassification/pull/584))
+
 ## v0.18.0(30/11/2021)
 
 ### Highlights

docs/en/install.md

@@ -11,6 +11,7 @@ The compatible MMClassification and MMCV versions are as below. Please install t
 | MMClassification version |     MMCV version      |
 |:------------------------:|:---------------------:|
 | master                   | mmcv>=1.3.16, <=1.5.0 |
+| 0.19.0                   | mmcv>=1.3.16, <=1.5.0 |
 | 0.18.0                   | mmcv>=1.3.16, <=1.5.0 |
 | 0.17.0                   | mmcv>=1.3.8, <=1.5.0  |
 | 0.16.0                   | mmcv>=1.3.8, <=1.5.0  |

docs/zh_CN/install.md

@@ -11,6 +11,7 @@ MMClassification 和 MMCV 的适配关系如下，请安装正确版本的 MMCV
 | MMClassification 版本 |       MMCV 版本       |
 |:---------------------:|:---------------------:|
 |        master         | mmcv>=1.3.16, <=1.5.0 |
+|        0.19.0         | mmcv>=1.3.16, <=1.5.0 |
 |        0.18.0         | mmcv>=1.3.16, <=1.5.0 |
 |        0.17.0         | mmcv>=1.3.8, <=1.5.0  |
 |        0.16.0         | mmcv>=1.3.8, <=1.5.0  |

mmcls/models/utils/helpers.py

@@ -1,14 +1,14 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import collections.abc
 import warnings
-from distutils.version import LooseVersion
 from itertools import repeat
 
 import torch
+from mmcv.utils import digit_version
 
 
 def is_tracing() -> bool:
-    if LooseVersion(torch.__version__) >= LooseVersion('1.6.0'):
+    if digit_version(torch.__version__) >= digit_version('1.6.0'):
         on_trace = torch.jit.is_tracing()
         # In PyTorch 1.6, torch.jit.is_tracing has a bug.
         # Refers to https://github.com/pytorch/pytorch/issues/42448

mmcls/version.py

@@ -1,6 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved
 
-__version__ = '0.18.0'
+__version__ = '0.19.0'
 
 
 def parse_version_info(version_str):

tests/test_models/test_utils/test_misc.py

@@ -1,8 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
-from distutils.version import LooseVersion
-
 import pytest
 import torch
+from mmcv.utils import digit_version
 
 from mmcls.models.utils import channel_shuffle, is_tracing, make_divisible
 
@@ -41,7 +40,7 @@ def test_channel_shuffle():
 
 
 @pytest.mark.skipif(
-    LooseVersion(torch.__version__) < LooseVersion('1.6.0'),
+    digit_version(torch.__version__) < digit_version('1.6.0'),
     reason='torch.jit.is_tracing is not available before 1.6.0')
 def test_is_tracing():