The development kit I use is 6490 (778G). When I use snpe2.12 to load the yolov8s model (int8 quantized), it takes about 5.5 seconds to load. I try to analyze this process, I found that snpebuilder.build() takes most of time. So how can I save time ?
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 can try to run quantization(INT8) model on HTP backend that will speed up execution time.
BR.
Wei