I’m looking into getting a YOLOv5 model running on NNAPI.
The doc ((Prototype) Convert MobileNetV2 to NNAPI — PyTorch Tutorials 1.7.1 documentation) states that the range of supported operators is limited.
Is it possible to get the listing of supported ops?
What is the strategy of the framework in a situation where the model uses both supported and unsupported ops? Does it bail out of NNAPI completely, or uses split execution, like TFLite?
The listing of supported ops you can find here:
If operation is not supported - serialization will fail with exception pytorch/serializer.py at master · pytorch/pytorch · GitHub
Hi what was your progress to get the Pytorch Yolov5 model to run on NNAPI?