Skip to main content
AUzpa
Associate II
July 22, 2019
Solved

Tensorflow Lite support X-CUBE-AI 4.0.0

  • July 22, 2019
  • 2 replies
  • 1220 views

Hello,

I have noticed that the latest version of X-CUBE-AI (4.0.0) has support for Tensorflow Lite. Therefore I tried to analyze a SSD Mobilenet v1 network that I found on this blog post:

Link to blog post

Link to .tflite model

When analyzing the .tflite model, I have an error: "TOOL ERROR: Unkown layer type CUSTOM, stopping". I suspect that this comes from the post-processing operations that implement the non-maximum suppression.

Where can I see the list of supported TFLite operations? Also the list of supported Keras layers were removed from the Getting Started with X-CUBE-AI .pdf.

I couldn't find those lists elsewhere. I would really appreciate some help! Thank you and kind regards

    This topic has been closed for replies.
    Best answer by fauvarque.daniel

    A lot of technical documentation has been moved in the pack itself under the Documentation directory

    You can access it through STM32CubeMX with the online help of STM32CubeMX.

    Leave the cursor on the "Artificial Intelligence X-Cube-AI" mode checkbox, you should have a tooltip with a link on the documentation

    You can also access it directly in your home STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/4.0.0/Documentation/index.html

    2 replies

    fauvarque.daniel
    fauvarque.danielBest answer
    ST Employee
    July 22, 2019

    A lot of technical documentation has been moved in the pack itself under the Documentation directory

    You can access it through STM32CubeMX with the online help of STM32CubeMX.

    Leave the cursor on the "Artificial Intelligence X-Cube-AI" mode checkbox, you should have a tooltip with a link on the documentation

    You can also access it directly in your home STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/4.0.0/Documentation/index.html

    AUzpa
    AUzpaAuthor
    Associate II
    July 23, 2019

    Thank you! Found it in my /root folder.