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.
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Dear developer,
YOu might want to check the encoding or weights scope in your model
BR.
Wei