Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] Are you excited about the upcoming Keras 3.0? (alien.top)

submitted 11 months ago by hyxon4@alien.top to c/machinelearning@academy.garden

49 comments fedilink hide all child comments

Creator of Keras confirmed that the new version comes out in a few days. Keras becomes multi-backend again with support for PyTorch, TensorFlow and JAX. Personally, I'm excited to be able to try JAX without having to deep dive into documentation and entire ecosystem. What about you?

you are viewing a single comment's thread
view the rest of the comments

[–] Relevant-Yak-9657@alien.top 1 points 11 months ago

As the others said, it's a pain to reimplement common layers in JAX (specifically). PyTorch is much higher level in it's nn API, but personally I despise rewriting the amazing training loop for every implementation. That's why even JAX uses Flax for common layers, because why use an error prone operator like jax.lax.conv_from_dilated or whatever and fill its 10 arguments every time? I would rather use flax.linen.Conv2D or keras_core.layers.Conv2D in my Sequential layer and prevent debugging a million times. For PyTorch, model.fit() can just quickly suffice and later customized.