Open tzhang2014 opened 6 years ago
This could be due to how cuDNN treats grouped convolutions, CaffeNet has a few of those. But what kind of difference are we talking about here?
@Noiredd CuDNN 7 grouped convolution is not fast enough on MobileNet,why?
win7 SP1 ,GTX1080 , VS2013, cuda8.0 + cudnn7.1 consumes GPU memory and memory more than cuda8.0 + cudnn5.1 to test caffeNet , Why? THX