资源分类
》 资源 》算法》caffe-mobilenet-v3

caffe-mobilenet-v3

2020-02-07 | |  33 |   0 |   0

caffe-mobilenet-v3

Introduction

This is a personal Caffe implementation of MobileNetV3. For details, please read the original papers: Searching for MobileNetV3.

How to use

  1. Requirements for Caffe (see: Caffe installation instructions)

  2. Add new caffe layers and rebuild the caffe:

  3. Run test

    CPU:$CAFFE_ROOT/build/tools/caffe time -model mobilenet_v3_large_1.0.prototxt
GPU:$CAFFE_ROOT/build/tools/caffe time -model mobilenet_v3_large_1.0.prototxt -gpu 0

Performance on MobileNetV3

BackboneCPU-ForwardCPU-BackwardGPU-ForwardGPU-Backward
V3-Large 1.0134.55 ms140.23 ms15.44 ms21.79 ms
V3-Small 1.058.64 ms59.30 ms11.49 ms12.58 ms

TODO

  • More MobileNetV3 architectures.

  • Traning & validation.


上一篇：mobilenetv3.pytorch

下一篇：MobileNet-SSD-RealSense

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...