Deep-Metric-Learning-CVPR16
Deep-Metric-Learning-CVPR16 copied to clipboard
cudnn.hpp(126): Error: argument of type "int" is incompatible with parameter of type "cudnnNanPropagation_t"
I am trying to compile the Caffe submodule version but it gives the above mentioned error when building with cmake.
I am using CUDA 8.0 and cuDNN 5.1.5
Does this Caffe submodule version support cuDNN 5.1.5?
Thanks in advance !!
I have the same problem and don't know what to do. Did u solve it?