justinkay/coda

Consensus-Driven Active Model Selection (ICCV 2025 Highlight)

21
/ 100
Experimental

This helps data scientists and machine learning engineers efficiently choose the best pre-trained machine learning model for a specific image analysis task. You provide a collection of candidate models and unlabeled image data, and it guides you to label only the most informative data points. The outcome is the identification of the most suitable model with significantly less manual annotation effort.

No commits in the last 6 months.

Use this if you need to select the optimal image classification model from a large pool of existing models, but want to minimize the time and cost associated with manually labeling a validation dataset.

Not ideal if you are developing models from scratch or if your task does not involve selecting from a set of pre-trained image models.

model-selection image-classification data-labeling machine-learning-operations computer-vision
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Last pushed

Oct 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/justinkay/coda"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.