You can import demo projects from the Cube package downloaded by the IDE, but you cannot integrate the libraries in a CubeIDE project, because they use different drivers. All you're left with in the new IDE is low-level functions. Is there a software...
Using X-CUBE-AI 6.0.0, trying to import a tflite model of a RNN network, with both dense and LSTM layers, this error is returned. I can't find any information on that. Is there something that can be done?Thank you very much
I'll try to explain the problem better: does ST want us to use the new IDE or not? Because before you had examples, demos and convenient libraries, while there's nothing similar now.You can import a project from the cube package, that's a sort of wor...
Thank you, it was not very clear from the package name and description it it was suitable.Anyway, I find it a little "overkilled" just to use a peripheral, if you don't want to design a full GUI application.I created the project from "Software packs"...
I'm the original poster, in the meanwhile we solved by not using tf lite. We reduced the original model by downsampling the input data, and so reducing the input vector size. This reduced the RAM occupation and so we can use the original keras model.
Hi, I'm using tf 2.4.1, and converting a keras model to tflite. The problem happens with or without quantization.I'm attaching an example model.Thank you very muchhttps://drive.google.com/file/d/1dvC4nHtnFZNU4Ka5ETkwRb6BwUKeoYbp/view?usp=sharing