mirrors
/
mmpretrain
mirror of https://github.com/open-mmlab/mmpretrain.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
OpenMMLab Pre-training Toolbox and Benchmark
229 Commits
8 Branches
41 Tags
32 MiB
Python 98.4%
Cuda 1.2%
Shell 0.2%
C++ 0.2%
 
 
 
 
Go to file
LXXXXR e76c5a368d
[Feature] Support fp16 training (#178) 
* change mmcls fp16 to mmcv hook

* support fp16

* clean unnessary stuff
 		2021-03-17 15:53:55 +08:00
.github Revert "temporary solution to ci until new version of mmcv is avaliable (#127)" (#128) 2020-12-30 17:11:33 +08:00
configs [Feature] Support fp16 training (#178) 2021-03-17 15:53:55 +08:00
demo Visualize results on image demo (#58) 2020-10-10 16:33:27 +08:00
docs Bump version to 0.9.0 (#166) 2021-03-01 20:14:53 +08:00
mmcls [Feature] Support fp16 training (#178) 2021-03-17 15:53:55 +08:00
requirements Do not install mmcv through requirements (#90) 2020-11-19 00:00:12 +08:00
resources Add README 2020-07-12 00:06:54 +08:00
tests [Feature] Support solarize and posterize pipelines (#172) 2021-03-09 19:45:13 +08:00
tools [Feature] Support fp16 training (#178) 2021-03-17 15:53:55 +08:00
.gitignore bump version to 0.6.0 (#62) 2020-10-11 00:12:04 +08:00
.pre-commit-config.yaml Bump version to 0.7.0 (#129) 2020-12-31 16:41:45 +08:00
.readthedocs.yml add .readthedocs.yml 2020-07-13 01:08:40 +08:00
LICENSE Update readme (#3) 2020-07-13 12:55:34 +08:00
README.md Bump version to 0.9.0 (#166) 2021-03-01 20:14:53 +08:00
requirements.txt workflow: modify build, add deploy (#61) 2020-10-10 22:15:50 +08:00
setup.cfg remove unnecessary addopts (#164) 2021-02-25 14:09:03 +08:00
setup.py fix pypi release error (#64) 2020-10-11 00:26:34 +08:00

README.md

Build Status Documentation Status codecov license

Introduction

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

v0.9.0 was released in 1/3/2021. Please refer to changelog.md for details and 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

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.

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.