PyTorch-FilterResponseNormalizationLayer
PyTorch-FilterResponseNormalizationLayer copied to clipboard
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
Not sure why this occurs.
Setting torch.backends.cudnn.enabled=False fixes this issue. Unfortunately it also increases memory consumption.
This may also be related to GPU memory error. CDNN seems to throw weird error flags even if you've exceeded the GPU capacity. It might be worth for future users to try and reduce the batch size before attempting.