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-0.5.0.tar.gz (69.3 kB view details)

Uploaded Source

Built Distribution

zcls-0.5.0-py2.py3-none-any.whl (140.3 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file zcls-0.5.0.tar.gz.

File metadata

  • Download URL: zcls-0.5.0.tar.gz
  • Upload date:
  • Size: 69.3 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-0.5.0.tar.gz
Algorithm Hash digest
SHA256 717b89bfe8c40e1092cca3be530aa99bd5aab6915fd5aa5a77c6d549ec200d05
MD5 9235d61e99fd1b07e2ee512999011eca
BLAKE2b-256 0accc407677bfbfdb354957107849816d49b4522b3fc2c84f5ee6ccf133fae17

See more details on using hashes here.

File details

Details for the file zcls-0.5.0-py2.py3-none-any.whl.

File metadata

  • Download URL: zcls-0.5.0-py2.py3-none-any.whl
  • Upload date:
  • Size: 140.3 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-0.5.0-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 38005edb34c333f89e2f235662a21f4c476a5479431fda58d7f1a5808f483506
MD5 d508eb426e4b6913f3c169af699ef477
BLAKE2b-256 ca04c457d461069ee3d2a150fae2ca61417dbad3479f35d85e840ad8f1930b7c

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