Forums - When will Matmul be supported?

2 posts / 0 new
Last post
When will Matmul be supported?
malila
Join Date: 9 Jun 21
Posts: 3
Posted: Wed, 2022-02-09 23:17

onnx model with a single matmul op. 

C = A @ B

A: [4, 3] is a constant weight

B: [3, 4] is a input.

 

[Instance 0 - cpu_float32] Unable to successfully create SNPE instance. Will continue to creation of other SNPE instance(s).container=matmul.dlc; perf_profile=burst;  error_code=1004; error_message=Layer parameters combination is invalid. error_code=1004; error_message=Layer parameters combination is invalid. Layer MatMul_1: mismatch between output size (4) and size of bias (3); error_component=Model Validation; line_no=1993; thread_id=548395827568; error_component=Model Validation; line_no=267; thread_id=548410130448
Warning: Requested 1 instances of SNPE, only able to create 0 instances. Continuing to execution with created instances.
Total throughput: 0 infs/sec
 
Can you support this type of Matmul?
  • Up0
  • Down0
weihuan
Join Date: 12 Apr 20
Posts: 270
Posted: Thu, 2022-02-10 21:07

Dear customer,

Thanks for sharing the ops support to us. We will take a look for this.

Addtional, what's feature this model will be exectued?

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.