Software environment:

1. cuda_8.06

2. cudnn5005

Implementation error on cudnn for deep neural network:

Exception: ('The following error happened while compiling the node', GpuDnnConv{algo='small', inplace=True, num_groups=1}(GpuContiguous.0, GpuContiguous.0, GpuAllocEmpty{dtype='float32', context_name=None}.0, GpuDnnConvDesc{border_mode='valid', subsample=(1, 1), dilation=(1, 1), conv_mode='conv', precision='float32', num_groups=1}.0, Constant{1.0}, Constant{0.0}), '\n', 'Compilation failed (return status=1): In file included from C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\include/driver_types.h:53:0,\r.                  from C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\include/cudnn.h:63,\r.                 

Solution: update the cudnn to the latest version (v7.0.5 as of 07/12/2018)