ManagedCUDA aims an easy integration of NVidia's CUDA in .net applications written in C#, Visual Basic or any other .net language.
440
stars
79
forks
source link
OpTensor for Double should accept CudaDeviceVariable<double> rather than CudaDeviceVariable<float> #37
Closed
cbovar closed 7 years ago
Thanks for the update to cuDNN v6.0!
I believe there is a small error in OpTensor method for doubles.