[Q] cudnnEngine.cpp (87) - Cuda Error in initializeCommonContext:

Dear Everyone.

I transfer the detection inference code to tensorrt.

but i got a error in below:

cudnnEngine.cpp (87) - Cuda Error in initializeCommonContext: 1 (Could not initialize cudnn, please check cudnn installation.)

I trained the caffemodel.
Parsing is success.
but It made error in image inference step.

What is problem?
is it memory problem?
memory is not enough?


Cuda error 1 usually points a device configuration error.

The device function being invoked (usually via cudaLaunchKernel()) was not previously configured via the cudaConfigureCall() function.

Try TRT 5 container nvcr.io/nvidia/tensorrt:18.09-py3 to rule out configuration issues.

If you continue to have this errors, please share a small repro package (containing source, model, dataset) which would help us debug.

I get the same problem. Have you solved it?