W0000 00:00:1714315704.778368 2252 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update

[sondosaabed]

Issue type

Others

Have you reproduced the bug with TensorFlow Nightly?

No

Source

source

TensorFlow version

2.15

Custom code

Yes

OS platform and distribution

Kaggle notebook

Mobile device

No response

Python version

3.12

Bazel version

No response

GCC/compiler version

No response

CUDA/cuDNN version

No response

GPU model and memory

No response

Current behavior?

What does this warning indicate and how does it affect the training

Standalone code to reproduce the issue

I have included an image in the upper cell. I see a warning when training

Relevant log output

No response

[tilakrayal]

@sondosaabed,
I suspect that this is due to Keras 3 which uses jit compile by default, and Keras 2 doesn't (user needs to explicitly enable jit), and the warning message is probably from jit/xla. I request you to take a look at this issue where a similar issue/warning has been proposed and it is still open. Also I request to follow the similar issue which has been proposed to have the updates on the similar issue. Thank you!

[sondosaabed]

@sondosaabed, I suspect that this is due to Keras 3 which uses jit compile by default, and Keras 2 doesn't (user needs to explicitly enable jit), and the warning message is probably from jit/xla. I request you to take a look at this issue where a similar issue/warning has been proposed and it is still open. Also I request to follow the similar issue which has been proposed to have the updates on the similar issue. Thank you!

Thank you for your reply! I suggest they make a better warning message so as a user I could easily understand what this is and how to fix it. I will check out the jit/xla !
Thank you for indicating that issue I'll follow up and see if it's affecting my training. I'm gonna close this issue with this...

[google-ml-butler]

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