mirrors
/
mmclassification
mirror of https://github.com/open-mmlab/mmclassification.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenMMLab Image Classification Toolbox and Benchmark
407 Commits
8 Branches
41 Tags
36 MiB
Python 99.7%
Shell 0.2%
Dockerfile 0.1%
 
 
 
Go to file
Ma Zerun 82713c9ba4
[Docs] Use docs link of other projects and add MMCV docs. (#511) 
* [Docs] Use docs link of other projects and add MMCV docs.

* Fix misused "document", and it should be "documentation"

* Fix uppercase

* Rename `Projects` to `Docs`.
 		2021-11-03 10:42:45 +08:00
.dev_scripts/benchmark_regression [Fix] Fix bug in `1-benchmark_valid.py` if checkpoint_root is None. (#489) 2021-10-25 12:01:03 +08:00
.github [Docs] Update `getting_started.md` and `install.md` and rewrite `finetune.md` (#466) 2021-09-28 18:05:50 +08:00
configs [Dependency] Update mmcv dependency version (#509) 2021-11-02 18:08:30 +08:00
demo [Docs] Add Copyright information. (#413) 2021-08-17 19:52:42 +08:00
docker [Dependency] Update mmcv dependency version (#509) 2021-11-02 18:08:30 +08:00
docs [Docs] Use docs link of other projects and add MMCV docs. (#511) 2021-11-03 10:42:45 +08:00
docs_zh-CN [Docs] Use docs link of other projects and add MMCV docs. (#511) 2021-11-03 10:42:45 +08:00
mmcls [Dependency] Update mmcv dependency version (#509) 2021-11-02 18:08:30 +08:00
requirements [Dependency] Update mmcv dependency version (#509) 2021-11-02 18:08:30 +08:00
resources
…
tests [Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467) 2021-10-29 10:37:16 +08:00
tools [Feature] Add a tool to find broken files. (#482) 2021-10-27 10:14:19 +08:00
.gitignore [Enhance] Improve downstream repositories compatibility (#421) 2021-09-08 10:38:57 +08:00
.pre-commit-config.yaml [Docs] Add code-spell pre-commit hook and fix a large mount of typos. (#470) 2021-10-13 14:33:07 +08:00
.readthedocs.yml
…
CITATION.cff [Docs] Add `CITATION.cff` (#428) 2021-09-01 17:07:27 +08:00
LICENSE [Docs] Add Copyright information. (#413) 2021-08-17 19:52:42 +08:00
MANIFEST.in
…
README.md Bump version to v0.17.0 (#503) 2021-10-29 14:04:03 +08:00
README_zh-CN.md Bump version to v0.17.0 (#503) 2021-10-29 14:04:03 +08:00
model-index.yml [Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467) 2021-10-29 10:37:16 +08:00
requirements.txt
…
setup.cfg [Tool] Add a tool to test TorchServe. (#468) 2021-10-14 17:56:32 +08:00
setup.py [Docs] Add `CITATION.cff` (#428) 2021-09-01 17:07:27 +08:00

README.md

Build Status Documentation Status codecov license

Introduction

English | 简体中文

MMClassification is an open source image classification toolbox based on PyTorch. It is a part of the OpenMMLab project.

Documentation: https://mmclassification.readthedocs.io/en/latest/

demo

Major features

  • Various backbones and pretrained models
  • Bag of training tricks
  • Large-scale training configs
  • High efficiency and extensibility

License

This project is released under the Apache 2.0 license.

Changelog

v0.17.0 was released in 29/10/2021.

Highlights of the new 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!

Please refer to changelog.md for more details and other release history.

Benchmark and model zoo

Results and models are available in the model zoo.

Supported backbones:

  • ResNet
  • ResNeXt
  • SE-ResNet
  • SE-ResNeXt
  • RegNet
  • ShuffleNetV1
  • ShuffleNetV2
  • MobileNetV2
  • MobileNetV3
  • Swin-Transformer

Installation

Please refer to install.md for installation and dataset preparation.

Getting Started

Please see getting_started.md for the basic usage of MMClassification. There are also tutorials for finetuning models, adding new dataset, designing data pipeline, and adding new modules.

Citation

If you find this project useful in your research, please consider cite:

@misc{2020mmclassification,
    title={OpenMMLab's Image Classification Toolbox and Benchmark},
    author={MMClassification Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmclassification}},
    year={2020}
}

Contributing

We appreciate all contributions to improve MMClassification. Please refer to CONTRUBUTING.md for the contributing guideline.

Acknowledgement

MMClassification is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new classifiers.

Projects in OpenMMLab

  • MMCV: OpenMMLab foundational library for computer vision.
  • MIM: MIM Installs OpenMMLab Packages.
  • MMClassification: OpenMMLab image classification toolbox and benchmark.
  • MMDetection: OpenMMLab detection toolbox and benchmark.
  • MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
  • MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
  • MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
  • MMTracking: OpenMMLab video perception toolbox and benchmark.
  • MMPose: OpenMMLab pose estimation toolbox and benchmark.
  • MMEditing: OpenMMLab image and video editing toolbox.
  • MMOCR: OpenMMLab toolbox for text detection, recognition and understanding.
  • MMGeneration: OpenMMlab toolkit for generative models.