资源分类
》 资源 》算法》mxnet-center-loss

mxnet-center-loss

2020-04-03 | |  33 |   0 |   0

MxNet implementation of the paper: A Discriminative Feature Learning Approach for Deep Face Recognition

Requirements

pip install -r requirements.txt

Training

  1. Train with original softmax

$ python main.py --train --prefix=softmax

  1. Train with softmax + center loss

$ python main.py --train --center_loss --prefix=center-loss

Test

  1. Test with original softmax

$ python main.py --test --prefix=softmax

  1. Test with softmax + center loss

$ python main.py --test --prefix=center-loss

Image

Comparison Accuracy curve:

图片.png

Softmax

Training:

softmax-train.gif

Testing:

softmax-test.gif

Softmax + Center Loss

Training:

center-train.gif

Testing:

center-test.gif

上一篇：Keras-MNIST-center-loss-with-visualization

下一篇：MNIST-center-loss

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...