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

Improve inference export script #3071

Merged
merged 8 commits into from May 8, 2023
Merged

Improve inference export script #3071

merged 8 commits into from May 8, 2023

Conversation

simonusher
Copy link
Contributor

@simonusher simonusher commented May 7, 2023 •
edited

closes #3038

@simonusher simonusher marked this pull request as ready for review May 8, 2023 17:04
olliestanley
olliestanley reviewed May 8, 2023
View reviewed changes
Copy link
Collaborator

@olliestanley olliestanley left a comment

Choose a reason for hiding this comment

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

Thanks for this PR, changes look good, I have left some minor comments and will run it locally to test soon

inference/server/export.py Outdated Show resolved Hide resolved
inference/server/export.py Show resolved Hide resolved
inference/server/export.py Outdated Show resolved Hide resolved
@simonusher
Copy link
Contributor Author

simonusher commented May 8, 2023 •
edited

I'm glad to hear that. I've addressed your comments except for one. Please let me know if the performance is sufficient. I believe the relationship filters, as they are now, will use correlated subqueries so they might be suboptimal.
I'm not entirely sure how to test them properly at scale. Is there maybe a script that fills the development inference-db with dummy data?

@olliestanley
Copy link
Collaborator

I'm glad to hear that. I've addressed your comments except for one. Please let me know if the performance is sufficient. I believe the relationship filters, as they are now, will use correlated subqueries so they might be suboptimal. I'm not entirely sure how to test them properly at scale. Is there maybe a script that fills the development inference-db with dummy data?

There isn't a way of filling the inference DB with dummy data currently, this would be a useful addition though so I'll raise a new issue for it. There's some dummy data here which was used for filling the data collection backend DB, could maybe be reused

@olliestanley olliestanley enabled auto-merge (squash) May 8, 2023 18:20
@olliestanley olliestanley merged commit 75c8adc into LAION-AI:main May 8, 2023
1 check passed
@olliestanley
Copy link
Collaborator

Thank you for this PR!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@olliestanley olliestanley olliestanley approved these changes

@yk yk Awaiting requested review from yk yk is a code owner

@andreaskoepf andreaskoepf Awaiting requested review from andreaskoepf andreaskoepf is a code owner

@AbdBarho AbdBarho Awaiting requested review from AbdBarho AbdBarho is a code owner

Assignees
No one assigned
Labels
inference
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Improve inference export script
2 participants
@simonusher @olliestanley