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.

Sign up for GitHub

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

Jump to bottom

[Feature Request]: Implement a native Tensorflow model hander #25366

Closed
3 of 17 tasks
riteshghorse opened this issue Feb 7, 2023 · 2 comments · Fixed by #25496
Closed
3 of 17 tasks

[Feature Request]: Implement a native Tensorflow model hander #25366

riteshghorse opened this issue Feb 7, 2023 · 2 comments · Fixed by #25496
Assignees
@riteshghorse
Labels
done & done Issue has been reviewed after it was closed for verification, followups, etc. new feature P2 python run-inference
Milestone
2.46.0 Release

Comments

@riteshghorse
Copy link
Contributor

riteshghorse commented Feb 7, 2023 •
edited
Loading

What would you like to happen?

Currently we use the tensorflow model handler in tfx_bsl which has some constraints listed in #23584. Implement a new model handler with support for more types like numpy, tensors, etc.

  • Load an entire saved model
  • Load model with saved weights

Issue Priority

Priority: 2 (default / most feature requests should be filed as P2)

Issue Components

  • Component: Python SDK
  • Component: Java SDK
  • Component: Go SDK
  • Component: Typescript SDK
  • Component: IO connector
  • Component: Beam examples
  • Component: Beam playground
  • Component: Beam katas
  • Component: Website
  • Component: Spark Runner
  • Component: Flink Runner
  • Component: Samza Runner
  • Component: Twister2 Runner
  • Component: Hazelcast Jet Runner
  • Component: Google Cloud Dataflow Runner
@riteshghorse riteshghorse self-assigned this Feb 7, 2023
@riteshghorse riteshghorse added this to the 2.46.0 Release milestone Feb 7, 2023
@riteshghorse riteshghorse mentioned this issue Feb 7, 2023
Merged
3 tasks
@damccorm
Copy link
Contributor

damccorm commented Feb 8, 2023

@riteshghorse since this isn't a release blocker I'm going to remove the 2.46 milestone. If we get to it in time we can always add it back (and it will get automatically added if this issue is closed)

@damccorm damccorm removed this from the 2.46.0 Release milestone Feb 8, 2023
@riteshghorse
Copy link
Contributor Author

SGTM

@riteshghorse riteshghorse mentioned this issue Feb 15, 2023
Merged
3 tasks
@github-actions github-actions bot added this to the 2.46.0 Release milestone Feb 22, 2023
@damccorm damccorm added the done & done Issue has been reviewed after it was closed for verification, followups, etc. label Mar 7, 2023
@damccorm damccorm mentioned this issue Apr 17, 2023
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@riteshghorse riteshghorse

Labels
done & done Issue has been reviewed after it was closed for verification, followups, etc. new feature P2 python run-inference
Projects
None yet
Milestone
2.46.0 Release
Development

Successfully merging a pull request may close this issue.

[Python] Support loading of TF models with saved weights riteshghorse/beam
2 participants
@riteshghorse @damccorm