Oliver Guy

Setting `torch.backends.cudnn.benchmark = True` at the beginning of the script fixed it for me.

Hi John, No problem at all, and thanks for checking back ! I was indeed able to train, and I'm now working on crafting my own coco dataset. Regards, Oliver

Hey all, I'm having a similar error as @NicolaGugole using the training dataset downloaded through the provided shell script. Any tips on how to fix this would be greatly appreciated...

@NicolaGugole I only modified those in the json, but I'm having issues with CudNN not finding the convolution algorithm (see #54).

I would love to see this fixed, especially as iterating over RaggedTensors seems to not properly work in a lot of cases.