deepskies/SIDDA

SInkhorn Dynamic Domain Adaptation 🚰🎺

35
/ 100
Emerging

When you have images from different sources or conditions that a machine learning model struggles to classify accurately due to visual differences, this tool helps. It takes your image datasets from various 'domains' and outputs a more robust classification model. Data scientists, machine learning engineers, and researchers working with image classification across varying data sources would find this valuable.

No commits in the last 6 months.

Use this if your image classification model performs poorly when applied to new datasets that look slightly different from your training data, and you want to improve its accuracy without extensive manual fine-tuning.

Not ideal if you are working with non-image data or if your classification problem does not involve domain shift issues.

image-classification machine-learning domain-adaptation astronomy computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 26, 2025

Commits (30d)

0

Get this data via API

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

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