cuDNN error: CUDNN_STATUS_MAPPING_ERROR

[JeremyLinky]

Hi, when I set the fidelity_weight w to be greater than 0 in the inference stage, the following error occurs:

return F.conv2d(input, weight, bias, self.stride, RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR

Could you provide any solutions? Thanks.