Deep-Feature-Flow The program can be trained, but during the training,but: This convolution is not supported by cudnn, MXNET convolution is applied

The program can be trained, but during the training,but: This convolution is not supported by cudnn, MXNET convolution is applied

Open weilanShi opened this issue 6 years ago • 3 comments

The program can be trained, but during the training, it has always been the following program: This convolution is not supported by cudnn, MXNET convolution is applied. What caused this problem, mxnet configuration? Thank you for your answer.

Nov 25 '18 13:11 weilanShi

I have the same problem. Do you know the reason for this problem？thanks

Dec 16 '18 15:12 vivi0907

I have the same problem. Do you know the reason for this problem？thanks

I don't know how to solve this problem yet. If you know, please share it.

Dec 19 '18 02:12 weilanShi

楼上都是中国老铁吧？这个问题好像是mxnet版本和论文使用的版本不一致。我也遇到了这个问题，我是按照mxnet的官网安装的没有cuDNN加速，模型跑起来特别慢。最后我建立了一个qq群，希望真心研究学习的小伙伴能加入。964957091

Dec 20 '18 14:12 liurongdev

Deep-Feature-Flow Deep-Feature-Flow copied to clipboard

The program can be trained, but during the training,but: This convolution is not supported by cudnn, MXNET convolution is applied

Deep-Feature-Flow
Deep-Feature-Flow copied to clipboard