AllenCell / AllenCell/allencell-segmenter-ml

Model metadata

Open
#492 0 comments 0 reactions 0 assignees View on GitHub
🚨 high priority🚨 UI/UX
Dominant language
Python
Stars
5
Forks
3
PR merge metrics
No merged PRs in 30d

Description

We need a system for tracking model metadata for the models we upload to s3.

1. Define metadata schema
2. Define storage (**s3 meta**, file in model payload?)
3. support rules for disabling incompatible models (incompatible with the version of cyto-dl)
4. Provide modeling with a tool for uploading models (enforce metadata schema)
5. displaying relevant information in the metadata to the user on the download window.

Staging bucket for testing:
link: https://us-west-2.console.aws.amazon.com/s3/buckets/staging-aics-ml-segmenter-models?region=us-west-2&bucketType=general&tab=objects
arn: arn:aws:s3:::staging-aics-ml-segmenter-models
Ask infra to let you assume the `ml_segmenter_dev` role on aws to access this bucket

![Image](https://github.com/user-attachments/assets/1a3944bd-1fa5-46f9-8764-f5e43bc629dd)

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.