TFLite's max operator has wrong broadcasting behavior

[Co1lin]

1. System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 20.04.4 LTS
• TensorFlow installation (pip package or built from source): pip package
• TensorFlow library (version, if pip package or github SHA, if built from source): 2.11.0.dev20220914

2. Code

Provide code to help us reproduce your issues using one of the following options:

Option A: Reference colab notebooks

https://colab.research.google.com/drive/1SWl6-cWwk2zRkiNYifUXtzojSz_uUCxg?usp=sharing

Option B: Paste your code here or provide a link to a custom end-to-end colab

3. Failure after conversion

After converting to TFLite, the model produces tensor with wrong shape. This is inconsistent with normal TF runtime, and numpy behavior.

[mohantym]

Hi @Co1lin !
It is replicating in nightly but It was throwing converter error in 2.9 and 2.10. As the documentation on tf.maximum suggests you should use same shapes for both input and output.

Thank you!

[Co1lin]

Hi, thank you for the reply! Since the documentation of maximum also notes that "Note that maximum supports broadcast semantics for x and y" which means numpy style broadcasting is supported, it's better if TFLite can produce the same results as numpy and TF.

[mohantym]

Ok @Co1lin !
Thanks for the clarification. It is a valid bug then.

@sachinprasadhs !
Could you look at this issue. Attached gist in 2.9, 2.10 and nightly for reference.

Thank you!

[ganler]

@mohantym @sachinprasadhs It seems this bug only occurs when one of the arguments in max is tf.zeros. When setting it to tf.ones, the inferred shape will be correct.

[pkgoogle]

Hi,

Thank you for opening this issue. Since this issue has been open for a long time, the code/debug information for this issue may not be relevant with the current state of the code base.

The TFLite team is constantly improving the framework by fixing bugs and adding new features. We suggest you try the latest TensorFlow version with the latest compatible hardware configuration which could potentially resolve the issue. If you are still facing the issue, please create a new GitHub issue with your latest findings, with all the debugging information which could help us investigate.

Please follow the release notes to stay up to date with the latest developments which are happening in the TFLite space.

[github-actions]

This issue is stale because it has been open for 7 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions]

This issue was closed because it has been inactive for 7 days since being marked as stale. Please reopen if you'd like to work on this further.

[google-ml-butler]

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