open-edge-platform/anomalib
A library for benchmarking, developing, and deploying deep learning anomaly detection algorithms with experiment tracking and edge deployment support.

Velocity · 7d
+3.5
★ / day
Trend
→steady
star history
Anomalib is a Python library focused on anomaly detection using deep learning methods. It provides implementations of state-of-the-art anomaly detection and segmentation algorithms. The library includes experiment management, hyperparameter optimization, and supports edge inference via OpenVINO optimization. It is built on PyTorch and Lightning frameworks for standardized model training and deployment.