Forums - Different results using uint8 and float as info

2 posts / 0 new
Last post
Different results using uint8 and float as info
jbvilliam
Join Date: 15 Jun 21
Posts: 2
Posted: Fri, 2022-04-08 05:15
Dear Customer,
 
To calculate the input tensor from float to fix point on the SNPE, we get the encoding from the model information.
 
You can learn more about how to register a float tensor at a fixed point by following the example in the Snap test code.
tnx gentleman
  • Up0
  • Down0
weihuan
Join Date: 12 Apr 20
Posts: 270
Posted: Sun, 2022-04-17 20:34

Dear customer,

You can take a look steps for float to fixed conversion from SNPE sample code. That will help you so much in data transition.

BR.
Wei

  • Up0
  • Down0
or Register

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.