abc-125/viad-benchmark

Benchmark for Visual Industrial Anomaly Detection

22
/ 100
Experimental

This project helps operations engineers and quality control managers evaluate visual industrial anomaly detection models for real-world manufacturing and inspection tasks. It takes various datasets and anomaly detection models as input and produces a benchmark of their performance, highlighting how practical aspects like input size and noisy data affect defect detection. This helps users understand which models are most reliable for identifying manufacturing defects or unusual patterns on production lines.

No commits in the last 6 months.

Use this if you need to objectively compare different visual anomaly detection models to find the best one for your industrial inspection pipeline, moving beyond academic claims.

Not ideal if you are looking for a pre-built, ready-to-deploy anomaly detection system rather than a tool for evaluating existing models.

industrial-inspection quality-control manufacturing defect-detection operations-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Aug 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/abc-125/viad-benchmark"

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