Is this a MXNet version implementation of mobilenet?
ysh329 opened this issue · 4 comments
ysh329 commented
I'm a little confused about README.md
.
You wrote: This model is converted from MobileNet-Caffe
. However, I found the operator your implemented channelwise_convolution.cc
,channelwise_convolution.cu
in mxnet@c492b5b.
Besides, does this channelwise
equal to depth-wise
convolution in original paper?
KeyKy commented
@ysh329 Sorry. i just copy the README.md from caffe. I only give a pretrained model. I am also waiting for high speed depth-wise convolution
ysh329 commented
@KeyKy My big brother, do u have email or wechat. I'm to implement a high perforance depth-wise convolution 😆
KeyKy commented
@ysh329 370846270@qq.com
wechat: xiaozhenyouni
Nice!