I was wondering if anyone has tried converting this Pytorch implementation of Mask RCNN in the ONNX format. I've been attempting to do it but keep running into errors.
I have the same issue. It is exporting a model with countless warning, and afterwards is essentially useless and only errors while using onnxruntime. If anyone done it before, please let me know too.
Hey guys,
I was wondering if anyone has tried converting this Pytorch implementation of Mask RCNN in the ONNX format. I've been attempting to do it but keep running into errors.