Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[TF 2.0 API Docs] tf.lite.TFLiteConverter #25844

margaretmz opened this issue Feb 18, 2019 · 2 comments


Copy link

commented Feb 18, 2019

System information

Describe the documentation issue

  • Links (Fixed)

Incorrect -
Correct -

This is used to convert from a TensorFlow "GraphDef or SavedModel" into either a TFLite FlatBuffer or graph visualization.

Should be "…GraphDef, Saved Model or tf.keras model…"

  • Usage example (In PR #26067)

This line of code should be repeated for each of the methods
open("converted_model.tflite", "wb").write(tflite_model)

  • Parameters Defined (Fixed)

Missing 2 parameters

  • optimizations
  • representative_dataset

We welcome contributions by users. Will you be able to update submit a PR (use the doc style guide) to fix the doc Issue?


margaretmz added a commit to margaretmz/tensorflow that referenced this issue Feb 24, 2019
Updates description & example usage
Made changes per issue tensorflow#25844:
- Updated description to mention tf.Keras model. 
- Added the missing line in the example usage for SavedModel and tf.keras model.

This comment has been minimized.

Copy link

commented Mar 2, 2019

Is this issue still unsolved? The PR seems to have solved it but it isn't still merged? Does that mean something is still left?


This comment has been minimized.

Copy link
Contributor Author

commented Mar 3, 2019

I'm waiting for PR #26067 to merge.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.