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@lemmy.nz
    link
    fedilink
    arrow-up
    2
    ·
    1 month 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.