grecosalvatore/DriftLensDemo

Drift Lens Demo

12
/ 100
Experimental

This web application helps machine learning practitioners monitor their deep learning models deployed in real-world scenarios. It takes a stream of unstructured data, like text, and flags when the model's understanding of that data starts to change over time without requiring new labels. This is crucial for anyone managing deep learning models on live data.

No commits in the last 6 months.

Use this if you need to know when your deep learning model for unstructured data, such as a text classifier, is performing differently due to changes in the real-world data it processes, even when you don't have new labels for supervision.

Not ideal if your models work with structured data, or if you need to detect drift only when new labels are available to retrain or re-evaluate the model.

machine-learning-operations deep-learning-monitoring unstructured-data-analysis model-drift-detection text-classification
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Python

License

Last pushed

Apr 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/grecosalvatore/DriftLensDemo"

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