Forums - How to generate an int16 precision model on snpe2.7

2 posts / 0 new
or Register
Last post
How to generate an int16 precision model on snpe2.7
zzy913
Join Date: 10 Dec 18
Posts: 3
Posted: Mon, 2023-03-06 00:34
Top

I tried to use the following parameters to generate an itn16 precision model, but the following error occurred. How to fix the error?

<blockquote>

--bitwidth 16 --enable_htp  --override_params

[INFO] InitializeStderr: DebugLog initialized.
[INFO] Processed command-line arguments
[ERROR] IrQuantizer: Unsupported weight bitwidth: 16
[INFO] DebugLog shutting down.
[INFO] InitializeStderr: DebugLog initialized.
[WARNING] SNPE HTP Offline Prepare: Matching record found. Skipping generating cache record for HTP_V73_SM8550_8MB.
[INFO] SNPE HTP Offline Prepare: Skipped cache generation for SM8550
</blockquote>
  • Up0
  • Down0
Re: How to generate an int16 precision model on snpe2.7
v.bathini
Join Date: 27 Feb 22
Posts: 11
Posted: Thu, 2023-03-09 17:45
Top
Hi zzy913 It won't support 16 bitwidth. It will support only 4 and 8 bitwidth
  • 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.