Issues about training on caffe
leochli opened this issue · 1 comments
leochli commented
Hi Austing,
You said there is not an optimized Depthwise conv layer in caffe.
I found there're 2 dw conv implementations:
https://github.com/BVLC/caffe/pull/5665/files
https://github.com/yonghenglh6/DepthwiseConvolution
Are they not good enough during your experiment? Or is there any other reasons for not training in caffe?