Hello
I am currently using QNN 2.11 to convert and quantize an ONNX model which have multiple head. One of the output is head pose,
the value for yaw is limited to an upper bound and it doesn't change no mattter if we increase the bitwidth. I was wondering if any one had suc a issue before? Please share your solution.
Dear developer,
YOu might want to check the encoding or weights scope in your model
BR.
Wei