2025-05-16 2:46 AM
Hello everyone,
I have a GRU-based model that I trained using PyTorch and then exported to ONNX. I'm trying to run it on various ST boards.
According to this documentation: ST Neural-ART Operator Support
it seems that the Neural-ART accelerator does not support the GRU layer. However, from what I understand, other ST Edge AI boards should support it—with some limitations described here: ONNX Supported Ops
That said, when I try to compile the model using the ST Edge AI Developer Cloud, I get the following error:
TOOL ERROR: operands could not be broadcast together with shapes (512,) (256,)
This is the same issue I previously encountered here: Community Thread - GRU/LSTM Model Issue
At this point, I'm not sure whether GRU layers are simply not supported at all, or if there's a way to make them work under specific conditions.
I'm attaching the ONNX model in case it helps.
Thanks in advance for any support or suggestions!
2025-05-22 7:44 AM
Hello @Dresult,
Sorry for all these issues. GRU and LSTM are still badly supported.
Our team is working on it but also on a lot of other subject.
I opened an internal ticket with your model.
I will try to keep you informed but it may take a lot of time before being worked one.
Have a good day,
Julian
2025-05-22 7:52 AM
Thanks Julian, I really appreciate that.
Don't worry, I asked mainly to understand if it was a problem of my model or not...