Skip to main content

Object Classification Code Base

Project description

Language: 🇺🇸 🇨🇳

«ZCls» is a classification model benchmark code base

Documentation Status

Supported Recognizers:

Refer to roadmap for details

Table of Contents

Background

In order to further improve the algorithm performance, it is usually necessary to improve the existing model, which inevitably involves code refactoring. Creating this repo, on the one hand, serves as the CodeBase of the new model/optimization method, on the other hand, it also records the comparison between the custom model and the existing implementation (such as Torchvision Models)

Installation

See INSTALL

Usage

How to train, see Get Started with ZCls

Use builtin datasets, see Use Builtin Datasets

Use custom datasets, see Use Custom Datasets

Maintainers

  • zhujian - Initial work - zjykzj

Thanks

@misc{ding2021repvgg,
      title={RepVGG: Making VGG-style ConvNets Great Again}, 
      author={Xiaohan Ding and Xiangyu Zhang and Ningning Ma and Jungong Han and Guiguang Ding and Jian Sun},
      year={2021},
      eprint={2101.03697},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{fan2020pyslowfast,
  author =       {Haoqi Fan and Yanghao Li and Bo Xiong and Wan-Yen Lo and
                  Christoph Feichtenhofer},
  title =        {PySlowFast},
  howpublished = {\url{https://github.com/facebookresearch/slowfast}},
  year =         {2020}
}

@misc{zhang2020resnest,
      title={ResNeSt: Split-Attention Networks}, 
      author={Hang Zhang and Chongruo Wu and Zhongyue Zhang and Yi Zhu and Haibin Lin and Zhi Zhang and Yue Sun and Tong He and Jonas Mueller and R. Manmatha and Mu Li and Alexander Smola},
      year={2020},
      eprint={2004.08955},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{ding2019acnet,
      title={ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks}, 
      author={Xiaohan Ding and Yuchen Guo and Guiguang Ding and Jungong Han},
      year={2019},
      eprint={1908.03930},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{howard2019searching,
      title={Searching for MobileNetV3}, 
      author={Andrew Howard and Mark Sandler and Grace Chu and Liang-Chieh Chen and Bo Chen and Mingxing Tan and Weijun Wang and Yukun Zhu and Ruoming Pang and Vijay Vasudevan and Quoc V. Le and Hartwig Adam},
      year={2019},
      eprint={1905.02244},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@misc{cao2019gcnet,
      title={GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond}, 
      author={Yue Cao and Jiarui Xu and Stephen Lin and Fangyun Wei and Han Hu},
      year={2019},
      eprint={1904.11492},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

For more thanks, check THANKS

Contributing

Anyone's participation is welcome! Open an issue or submit PRs.

Small note:

License

Apache License 2.0 © 2020 zjykzj

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

zcls-0.4.1.tar.gz (68.8 kB view details)

Uploaded Source

Built Distribution

zcls-0.4.1-py2.py3-none-any.whl (139.8 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file zcls-0.4.1.tar.gz.

File metadata

  • Download URL: zcls-0.4.1.tar.gz
  • Upload date:
  • Size: 68.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4

File hashes

Hashes for zcls-0.4.1.tar.gz
Algorithm Hash digest
SHA256 92692d83ade7119851ed46d40b53a94968b4a06fe4947e3b0d4eb973c78e45ef
MD5 bcb5d90181f7d9f7db92d1d36950a560
BLAKE2b-256 9b39e3f8fe0578594effda513adb7c7bdb2f9878973a1ba26ae8f8cfd7c9da38

See more details on using hashes here.

File details

Details for the file zcls-0.4.1-py2.py3-none-any.whl.

File metadata

  • Download URL: zcls-0.4.1-py2.py3-none-any.whl
  • Upload date:
  • Size: 139.8 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4

File hashes

Hashes for zcls-0.4.1-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 6086549ff1f3b47bef40b9147bf983222532b2427af657cbedc3037155c4a6f0
MD5 ec328955166c4e0e792c97eb4de4f896
BLAKE2b-256 9e16e989efe64ac1035363d9d9404d18b1f1a8816bec4dba286344041e8cc3ca

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page