6.2: Converting Python saved models with the TensorFlow.js command line converter

Поділитися
Вставка
  • Опубліковано 27 січ 2025

КОМЕНТАРІ • 12

  • @GoogleDevelopers
    @GoogleDevelopers  Рік тому +2

    Catch more episodes from Machine Learning for Web Developers (Web ML) → goo.gle/learn-WebML

  • @billyboy3777
    @billyboy3777 Рік тому +1

    You are perfect! For a long time I tried to run it locally on my windows system but failed every time. You saved my with google collab. Respect!

  • @RobOlsen42
    @RobOlsen42 Рік тому +3

    Although I've been enjoying this series, it is disheartening that this particular video that was made by Google developers and uses Google Colab no longer works after only 3 months. When following the instructions on Colab, the code returns a "TF-TRT Warning: Could not find TensorRT" error when attempting to run the tensorflowjs_converter. I can't find any resolutions to this issue, and can't move forward if we're going to be building on these concepts in the next video.

    • @lokidarkbeard2647
      @lokidarkbeard2647 Рік тому

      I have the same issue. I also couldn't run it on the WSL2 setup that had everything installed. Looks like even with the errors it creates the files. I was able to continue the series.

    • @karimkalboussi4703
      @karimkalboussi4703 10 місяців тому

      same problem, did you find any solution please ?

    • @karimkalboussi4703
      @karimkalboussi4703 10 місяців тому

      @@lokidarkbeard2647 same problem, did you find any solution please ?

    • @lokidarkbeard2647
      @lokidarkbeard2647 10 місяців тому

      @karimkalboussi4703 even though it gives errors, it still produces the files you need.

  • @DimensionPardo
    @DimensionPardo 10 місяців тому

    I get the following error: Exception: Error dumping weights, duplicate weight name kernel

  • @riefki-inanutshell5359
    @riefki-inanutshell5359 14 днів тому

    can i convert my models.json to models.h5?

  • @benbrahimilias426
    @benbrahimilias426 4 місяці тому

    is it possible to do the opposite ?