I had to downgrade from TensorFlow 2.18.0 to 2.12.0 recently so that I can turn my model into a CoreML model. And coremltools only supports TensorFlow 2.12.0.

After doing that, training my model is taking roughly 3-4x longer than it did on 2.18.0.

  • jack
    link
    fedilink
    arrow-up
    1
    ·
    30 days ago

    It could be to do with Keras 3 becoming the new default after 2.16.0. They also deprecated tensorflow-macos in favor of a unified installation method so it’s possible internal changes made in the consolidated package account for the recent improvements.

      • jack
        link
        fedilink
        arrow-up
        2
        ·
        29 days ago

        Yep, it essentially just provides a bunch of useful building blocks for networks and some time-saving tools so you don’t have to create them yourself using TensorFlow primitives.