Error in execution of pass type(OPT_RM_TRANSPOSE_MATMUL) id(16)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-03-29 12:07 AM
I used the cmd on Windows and entered the following command: "stedgeai.exe analyze --target stm32f4 --name network -m CNN_Attention_MLP1.onnx --verbosity 3 --no-onnx-optimizer".
Then I got the error message as mentioned in the title. When the "--no-onnx-optimizer" parameter was not used, I would get similar DEBUG information. They were all "Error in execution of pass type(OPT_RM_TRANSPOSE_MATMUL) id(16)" as shown in the subject, which really confused me.
Since I had turned off the ONNX optimizer, it was strange that it still reported an error here. The attachment is my debug log and the ONNX model.
- Labels:
-
STM32CubeAI
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-03-31 6:01 AM - edited ‎2025-04-01 7:34 AM
Hello @Nephalem ,
Matmul is badly supported in the ST Edge AI Core 2.0 causing the error.
Internally, your model works without any issues.
The next update is planned for April.
Can you please wait for it?
Have a good day,
Julian
In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
‎2025-04-28 12:46 AM
Hello
It's already the end of April. Will there be any updates in April?
If not, please let me know so I can move to another platform for deployment. Thank you.
Have a nice day!
