CUBE-AI 8.0 INTERNAL ERROR: list index out of range

[Alpha_Lee]

STM32 CubeAI v1.7.0 (STM.ai v8.0.0-19389)
error: list index out of range

• This is a model created and transformed using pytorch

  

  • Is the model too big?

[Issamos]

Hello @Alpha_Lee 

Can you rewrite your question in English for two reasons. First, English is the official language of the community. Also, our community members and experts can easily understand your question and answer it.

Best regards.

II

[fauvarque.daniel]

Please share your model (could be with fake weights) so we can reproduce the issue.

The error you see is very likely a limitation in the current version of the tool, are you using 1D layers ?

Regards

[Alpha_Lee]

Yeah, you're right.I rewrote it.

[Alpha_Lee]

The model size is 20M and I can't upload it. Is it because the model is too big?

[Mai1]

Have you tried quantizing the model?

[mbg82]

Hello @fauvarque.daniel ,

can you explain the current limitation of the tool? I'm also facing issues when loading quantized onnx model created with pytorch (LSTM model). Getting following error in my case (both developer cloud and CubeMX :(

Neural Network Tools for STM32 family v1.7.0 (stm.ai v8.1.0-19520)
INTERNAL ERROR: create_layer() missing 2 required positional arguments: 'formats' and 'shapes'

Regards

[fauvarque.daniel]

try to zip it, alternatively you can share a link on this page

Thanks

[fauvarque.daniel]

Can you also share the onnx model. 

[mbg82]

@fauvarque.daniel thanks for quick support!