Forums - using snpe-dlc-quantize to tf model returns wrong results

1 post / 0 new
using snpe-dlc-quantize to tf model returns wrong results
Join Date: 28 Dec 18
Posts: 4
Posted: Mon, 2019-02-11 21:15
I'm using snpe-dlc-quantize to quantize a tensorflow model MobileNetV1,then run it on DSP.But the result is wrong,unquantized model result is correct ,instead.
By the way,quantized caffe MobileNetV1 model which is running on DSP return correct results.
I've tried using use_enhanced_quantizer ,but make no difference.So Is there any way to solve the problem?
snpe version:1.22
  • 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.