资源算法Shufflenet-v2-Pytorch

Shufflenet-v2-Pytorch

2020-01-16 | |  39 |   0 |   0
Shufflenet-v2-Pytorch 
Introduction

This is a Pytorch implementation of faceplusplus's ShuffleNet-v2. For details, please read the following papers: 
	ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Pretrained Models on ImageNet

We provide pretrained ShuffleNet-v2 models on ImageNet,which achieve slightly better accuracy rates than the original ones reported in the paper.

The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN): 
Network 		Top-1 	Top-5	Top-1(reported in the paper) 
ShuffleNet-v2-x0.5 	60.646 	81.696	60.300
ShuffleNet-v2-x1 	69.402 	88.374	69.400


Evaluate Models 
python eval.py -a shufflenetv2 --width_mult=0.5 --evaluate=./shufflenetv2_x0.5_60.646_81.696.pth.tar ./ILSVRC2012/
python eval.py -a shufflenetv2 --width_mult=1.0 --evaluate=./shufflenetv2_x1_69.390_88.412.pth.tar ./ILSVRC2012/

Version:
Python2.7
torch0.3.1
torchvision0.2.1

Dataset prepare Refer to https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md#download-the-imagenet-dataset


上一篇: ShuffleNet_V2_pytorch_caffe

下一篇:keras-shufflenetV2

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...