Model fails to train with Linux and Keras 3.3.2 about keras

[sachinprasadhs]

@t-kalinowski , I just updated the latest release tag in the landing page

[fchollet]

Any advice on what may be causing the issue? Let me know if there is any information that I can provide to help troubleshoot the issue.

This code is known to work, so it's likely a bad initialization. Some common steps you can take:

• Just restart and try again (with a different random seed)
• Lower the learning rate by 2x
• Lower dropout rate (0.5 -> 0.25)

[t-kalinowski]

@fchollet I am able to reproduce this. I haven't had a chance to dig into the root cause yet, but I can confirm that this is a bug in Keras 3; the same code produces a model that trains just fine w/ TF 2.15 + Keras 2.

[fchollet]

Looking into it.

[fchollet]

I have fixed a related issue with dataset shuffling. Can you try installing v3.3.3 and checking if your code works with that version?

[t-kalinowski]

Thanks! Looks like it's fixed now. I can confirm the model trains fine with Keras v3.3.3

[jonbry]

Looks like v3.3.3 fixed the issue. Thanks for all of your help!

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No

[t-kalinowski]

By the way, just noticed that github release tagged v3.3.3 has a typo in the title (Kears vs Keras): Kears 3.3.3

Maybe this is the reason v3.3.2 is still listed as the "latest release" on the repo landing page?