Question/Issue:
I’ve trained an audio model using Edge Impulse - this was straightforward. I selected the “Alif DevKit Gen2 HE core” and Inference Engine “TensorFlow Lite”. These seemed the closed fit to my OpenMV AE3 - are these selections correct or do you recommend a better selection from the options?
I am trying to deploy to my OpenMV AE3 via the IDE but the file type .lite is generating an error. Error: Reading input file ‘fileXYZ.lite’: Unsupported file extension. Only .tflite and .tosa files are supported.
I don’t see how to create .tflite files using Edge Impulse… any suggestions appreciated…
Hi @RichardWOttawa
the OpenMV team is investigating this issue, I will report here their findings.
regards,
fv
ps: you can try to simply rename the .lite to .tflite and you can download the TensorFlow Lite file directly from the Dashboard of your project.
Yes - I’ve successfully downloaded the renamed files but now that I’ve been able to load the .tflite model into ROM FS by renaming the .lite files to .tflite files I have a new error I’m trying to understand. When I run a script on the OpenMV AE3 the error message is ValueError: input shape does not match the model input shape.
I presume this means that I’ve selected incorrect deployment targets and inference engines?
From the Edge Impulse Deployment section I selected Deployment target: Alif Ai:ML Kit Gen2 HE core and the Infer once engine: TensorFlow Lite. I am using the OpenMV AE3 through the OpenMV IDE and I this seemed the closest match from the available selections.