Forums - quant model diff between SNPE dsp with TFLITE

1 post / 0 new
or Register
quant model diff between SNPE dsp with TFLITE
1559941035
Join Date: 20 May 21
Posts: 1
Posted: Thu, 2021-05-20 05:44
Top

 i use tfile to quantize my model, the model precision is good . then i write the  same range encodings to the snpe dlc quantized model. but the snpe dsp performance is poor.

I use the snpe debug mode to get the layer dequantized result, and compare to tflite dequantized result. I found that they differ by a scale,  as the number of layers increases, the difference gets bigger and bigger.

I am curious about how snpe dsp performs int8 convolution and int32 accumulator shifts round to int8, it seems difference with tflite, i think this is the reason for the big difference between the two

  • Up0
  • Down0

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.