https://github.com/zjcv/zcls2

More Faster Object Classification Training Framework
https://github.com/zjcv/zcls2

apex cccf image-classification pytorch zcls zcls2

Last synced: 20 days ago
JSON representation

More Faster Object Classification Training Framework

• Host: GitHub
• URL: https://github.com/zjcv/zcls2
• Owner: ZJCV
• License: apache-2.0
• Created: 2022-04-05T06:50:10.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2023-12-24T13:46:49.000Z (about 1 year ago)
• Last Synced: 2024-12-07T20:51:40.564Z (26 days ago)
• Topics: apex, cccf, image-classification, pytorch, zcls, zcls2
• Language: Python
• Homepage: https://zcls2.readthedocs.io/en/latest/
• Size: 326 KB
• Stars: 8
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGE.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  Language:

    🇺🇸

  🇨🇳







  «ZCls2» is a more faster classification model training framework







  

  

  

  




  

  

  

  

  




  

      

  

  

  

  

  

  

  



## Table of Contents

- [Table of Contents](#table-of-contents)

- [Background](#background)

- [Installation](#installation)

- [Usage](#usage)

- [Maintainers](#maintainers)

- [Thanks](#thanks)

- [Contributing](#contributing)

- [License](#license)

## Background

After nearly one and a half years of development, [ZCls](https://github.com/ZJCV/ZCls) has integrated many training features, includes configuration module, register module, training module, and many model implementations (`resnet/mobilenet/senet-sknet-resnest/acbnet-repvgg-dbbnet/ghostnet/gcnet...`) and so on. In the development process, it is found that compared with the current excellent classification training framework, such as [apex](https://github.com/NVIDIA/apex/tree/master/examples/imagenet), the training speed of [ZCls](https://github.com/ZJCV/ZCls) is not outstanding. 

In order to better improve the training speed, we decided to develop a new training framework [ZCls2](https://github.com/ZJCV/ZCls2), which is implemented based on [apex](https://github.com/NVIDIA/apex/tree/master/examples/imagenet) and provides more friendly and powerful functions. In the preliminary implementation, it can be found that [ZCls2](https://github.com/ZJCV/ZCls2) improves the training speed by at least 50% compared with [ZCls](https://github.com/ZJCV/ZCls).  More functions are being added.

## Installation

See [Install](https://zcls2.readthedocs.io/en/latest/install/)

## Usage

See [Get started](https://zcls2.readthedocs.io/en/latest/get-started/)

## Maintainers

* zhujian - *Initial work* - [zjykzj](https://github.com/zjykzj)

## Thanks

* [NVIDIA/apex](https://github.com/NVIDIA/apex/tree/master/examples/imagenet)

* [ZJCV/ZCls](https://github.com/ZJCV/ZCls)

## Contributing

Anyone's participation is welcome! Open an [issue](https://github.com/ZJCV/ZCls2/issues) or submit PRs.

Small note:

* Git submission specifications should be complied

  with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0-beta.4/)

* If versioned, please conform to the [Semantic Versioning 2.0.0](https://semver.org) specification

* If editing the README, please conform to the [standard-readme](https://github.com/RichardLitt/standard-readme)

  specification.

## License

[Apache License 2.0](LICENSE) © 2022 zjykzj