Skip to content

Latest commit

 

History

History
15 lines (7 loc) · 753 Bytes

README.md

File metadata and controls

15 lines (7 loc) · 753 Bytes

HENet

This is caffe implementation of HENet, For details, you can read the original paper:

"HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage" by Qiuyu zhu, Ruixin zhang. This model's cuda file for acceleration is based on farmingyard/ShuffleNet.

Note: If you want to train HENet in Caffe,you need to add ShuffleChannel layer to Caffe first. You can download from farmingyard/ShuffleNet. If you have no clue about how to add the ShuffleChannel layer, take this blog"ShuffleNet在Caffe框架下的实现" as a reference.