Closed wenhe-jia closed 7 years ago
Now you do not need to use ChannelwiseConvolution just use num_group in mxnet 0.11.1. I will delete the mobilenet-faster.py symbol.
@KeyKy @LeonJWH And Cudnn V7 support grouped conv now!
Good to hear that!
It approch 10% up in speed of normal conv.
In repo https://github.com/shicai/MobileNet-Caffe only regular conv layers are used with group=32 as depthwise conv layers, what about depthwise convolution? Is there any difference between standard convolution and depthwise convolution?
ok, thanks a lot!
I noticed that you have used ChannelwiseConvolution in
mobilenet-symbol.json
file andmobilenet-faster.py
. I am using mxnet of version 0.11.1, do i have to use ChannelwiseConvolution with depthwiseConvolution instead? Because your update say that mxnet 0.11.1 support depthwiseConvolution. Thanks for your reply!