简介

本仓库存储了 Efficientnetlite-b4 模型，与 Kalray 的神经网络 API 兼容。</br> 详情及正确用法请参阅 www.github.com/kalray/kann-models-zoo。</br> Efficientnet 模型说明请参阅 https://huggingface.co/docs/transformers/main/en/model_doc/efficientnet。</br>

内容

• ONNX: efficientnet-lite4-s.onnx
• 量化 ONNX: efficientnet-lite4-s-q.onnx

参考文献讲义

• EfficientNet: 重新思考卷积神经网络模型缩放, https://arxiv.org/pdf/1905.11946

仓库或链接参考

• https://github.com/onnx/models/blob/5faef4c33eba0395177850e1e31c4a6a9e634c82/vision/classification/efficientnet-lite4/model/efficientnet-lite4-11.onnx

BibTeX 条目及引用信息

@article{DBLP:journals/corr/abs-1905-11946,
  author       = {Mingxing Tan and
                  Quoc V. Le},
  title        = {EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
  journal      = {CoRR},
  volume       = {abs/1905.11946},
  year         = {2019},
  url          = {http://arxiv.org/abs/1905.11946},
  eprinttype    = {arXiv},
  eprint       = {1905.11946},
  timestamp    = {Mon, 03 Jun 2019 13:42:33 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1905-11946.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

作者: qmuller@kalrayinc.com, nbouberbachene@kalrayinc.com