Forums - For Inception-v3 model different results using gpu and dsp runtime.

1 post / 0 new
For Inception-v3 model different results using gpu and dsp runtime.
rahulrapatil007
Join Date: 8 Apr 18
Posts: 1
Posted: Thu, 2018-06-21 22:38

 Hi,
     
         I have done Benchmarking Inception-v3 model on Snapdragon q820 board.Performance of GPU is better  than DSP  but using dsp runtime accuracy of result decreases.
 
What is the reason for decrease in accuracy of result ?

 

Thanks,

Rahul Patil

  • 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.