MXNet-MobileNetV3

A Gluon implement of MobileNetV3

How to use it？

git clone https://www.github.com/deepinsight/insightface.git
cp $MXNet-MobileNetV3/fmobilenetv3.py $insightface/recognition/symbols

Then follow the insightface's parallel train usage to train face recognition, please.

Feel free to contact me

I am just a new to MXNet and Gluon, There must be soooo many bugs in fmobilenetv3.py. Feel free to contact me with issue or [email protected], I will solve it as soon as I could.

Reference

kuan-wang/pytorch-mobilenet-v3

    @ARTICLE{2019arXiv190502244H,
       author = {{Howard}, Andrew and {Sandler}, Mark and {Chu}, Grace and
         {Chen}, Liang-Chieh and {Chen}, Bo and {Tan}, Mingxing and
         {Wang}, Weijun and {Zhu}, Yukun and {Pang}, Ruoming and
         {Vasudevan}, Vijay and {Le}, Quoc V. and {Adam}, Hartwig},
        title = "{Searching for MobileNetV3}",
      journal = {arXiv e-prints},
     keywords = {Computer Science - Computer Vision and Pattern Recognition},
         year = "2019",
        month = "May",
          eid = {arXiv:1905.02244},
        pages = {arXiv:1905.02244},
    archivePrefix = {arXiv},
       eprint = {1905.02244},
    primaryClass = {cs.CV},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2019arXiv190502244H},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
    }