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

feat: added compile flag to bentoml.keras.load_model() #3949

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

MarioMarkov
Copy link

@MarioMarkov MarioMarkov commented Jun 10, 2023

What does this PR address?

When you load a model from a directory a warning is shown that the model is not compiled, to remove the warning you have to pass compile=False to keras load_model() function. The implementation of bentoml.keras.load_model() was missing this argument.

Fixes (#3948)

Before submitting:

@MarioMarkov MarioMarkov requested a review from a team as a code owner June 10, 2023 12:53
@MarioMarkov MarioMarkov requested review from aarnphm and removed request for a team June 10, 2023 12:53
@MarioMarkov MarioMarkov changed the title feat: added compile flag to keras.load_model() feat: added compile flag to bentoml.keras.load_model() Jun 10, 2023
Copy link
Contributor

@frostming frostming left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What about passing **kwargs to load_model() function? /cc @aarnphm

@aarnphm
Copy link
Member

aarnphm commented Jun 12, 2023

Ah we need to also support saving it and somehow handle kwargs during get_runnable

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants