Skip to content

xingmimfl/pytorch_ShuffleNet_ShuffleNetV2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ShuffleNet with PyTorch

Note: This project is pytorch implementation of ShuffleNet.

Performance

Trained on ImageNet with groups=3, get Prec@1 67.898% and Prec@5 87.994%. During the training, I set batch_size=256, learning_rate=0.1 which decayed every 30 epoch by 10.

Training on ImageNet

python main -b 256 $Imagenetdir

License: MIT license (MIT)

About

pytorch version of ShuffleNet and ShuffleNet V2

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages