资源分类
》 资源 》算法》mobilenet-mxnet

mobilenet-mxnet

2020-02-07 | |  31 |   0 |   0

MobileNet-MXNet

Introduction

This is a MXNet implementation of Google's MobileNets. For details, please read the original paper:

Pretrained Models on ImageNet

A pretrained MobileNet model on ImageNet is provided and you can use score.py to reproduce the accuracy in ImageNet 2012 val dataset.

The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN):

NetworkTop-1Top-5model size
MobileNet71.2490.1516.6MB
MobileNet-V271.6290.2713.8MB

Notes

  • RGB mean values [123.68,116.78,103.94] are subtracted

  • scale: 0.017 is used as std values for image preprocessing

  • This model is converted from MobileNet-Caffe

  • MXNet 11.0rc supports depthwiseConvolution now!


上一篇：darknet_mobilenet

下一篇：mobilenetv3.pytorch

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • 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 ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

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