Using snpe version 1.68
converted my model from onnx, it runs on android gpu.
no errors or warnings when using snpe-dlc-quantize
but when running -snpe-throughput-net-run --container fquant.dlc --duration 3 --use_dsp --perf_profile high_performance
Using snpe version 1.68
converted my model from onnx, it runs on android gpu.
no errors or warnings when using snpe-dlc-quantize
but when running -snpe-throughput-net-run --container fquant.dlc --duration 3 --use_dsp --perf_profile high_performance
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,
Could you please share your model with us through github, and we will run it locally to find the reason.
BR.
Yunxiang
Thank you Yunxiang.
You can find the quantized dlc in -
https://github.com/Gal147/dlcConverter