Anomalib | Awesome Repository

Anomalib is a PyTorch-based library for visual anomaly detection, offering a modular framework, a comprehensive model zoo, and a benchmarking suite designed for industrial defect detection. It provides a wide range of algorithms—including generative, discriminative, teacher-student, and vision-language approaches—that support unsupervised, few-shot, and zero-shot settings.

The library enables deployment through model export to ONNX and OpenVINO for edge devices, and includes a no-code web application for training and inference. It also features a command-line interface for orchestrating multi-stage pipelines, grid-search benchmarking across models and datasets, and experiment tracking with multiple logging backends.

Data loading and preprocessing support image, video, and depth modalities, along with synthetic anomaly generation. The library also provides automated result visualization and evaluation metrics for anomaly detection performance.

Features

Benchmarking Suites - Provides a benchmarking suite that evaluates multiple anomaly detection models across standard datasets.
Anomaly Detection Metrics - Computes a suite of standard metrics (AUROC, AUPR, F1, etc.) to measure anomaly detection performance.
Backbone Integrations - Uses pretrained neural network backbones to compute deep feature representations from input data.
Benchmarking Suites - Automates hyperparameter and model grid searches across accelerators and datasets, collecting metrics in parallel across worker processes.

Features

Benchmarking Suites - Provides a benchmarking suite that evaluates multiple anomaly detection models across standard datasets.
Anomaly Detection Metrics - Computes a suite of standard metrics (AUROC, AUPR, F1, etc.) to measure anomaly detection performance.
Backbone Integrations - Uses pretrained neural network backbones to compute deep feature representations from input data.
Benchmarking Suites - Automates hyperparameter and model grid searches across accelerators and datasets, collecting metrics in parallel across worker processes.