# open-edge-platform/anomalib

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/open-edge-platform-anomalib).**

5,401 stars · 874 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/open-edge-platform/anomalib
- Homepage: https://anomalib.readthedocs.io/en/latest/
- awesome-repositories: https://awesome-repositories.com/repository/open-edge-platform-anomalib.md

## Topics

`anomaly-detection` `anomaly-localization` `anomaly-segmentation` `geti` `neural-network-compression` `openvino` `unsupervised-learning`

## Description

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.

## Tags

### Data & Databases

- [Benchmarking Suites](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/benchmarking-suites.md) — Provides a benchmarking suite that evaluates multiple anomaly detection models across standard datasets.
- [Anomaly Detection Algorithms](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms.md) — Provides a comprehensive model zoo with ready-to-use implementations of anomaly detection algorithms for multiple settings. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/index.html))
- [Anomaly Detection Dataset Loaders](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/anomaly-detection-dataset-loaders.md) — Loads and prepares visual anomaly detection data from standard benchmarks and custom folders. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/data/datamodules.html))
- [Benchmarking Tools](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/benchmarking-tools.md) — Evaluates state-of-the-art anomaly detection methods on public and private datasets using built-in benchmarking tools. ([source](https://anomalib.readthedocs.io/en/latest/))
- [Custom Model Frameworks](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/custom-model-frameworks.md) — Provides core building blocks and utilities for assembling custom anomaly detection models from scratch. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/index.html))
- [Custom Dataset Loading](https://awesome-repositories.com/f/data-databases/data-loading-optimizations/custom-dataset-loading.md) — Anomalib loads image datasets from custom folders and standard formats, structuring them for model training and evaluation. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/data/index.html))
- [Inference Data Pipelines](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-processing/ml-data-pipelines/training-data-pipelines/inference-data-pipelines.md) — Applies trained models to new data to generate anomaly scores and segmentation maps. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/cli/index.html))
- [Benchmark Dataset Loaders](https://awesome-repositories.com/f/data-databases/static-benchmark-datasets/benchmark-dataset-loaders.md) — Provides ready-to-use PyTorch Dataset implementations for standard anomaly detection benchmarks. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/data/index.html))
- [Vision Dataset Loading](https://awesome-repositories.com/f/data-databases/vision-dataset-loading.md) — Anomalib loads standard and custom image datasets through dedicated datamodules, handling dataset-specific formats for anomaly detection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/data/datamodules/image/index.html))
- [Fast Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/fast-anomaly-detectors.md) — Anomalib uses a student-teacher architecture with contrastive learning to identify anomalous regions without requiring labeled anomalies. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/uninet.html))
- [Few-Shot Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/few-shot-anomaly-detectors.md) — Supports few-shot and zero-shot anomaly detection by comparing image regions to reference images using CLIP embeddings. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/winclip.html))
- [Zero-Shot Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/few-shot-anomaly-detectors/zero-shot-anomaly-detectors.md) — Anomalib uses a pre-trained vision foundation model to identify image-level and pixel-level anomalies without requiring training data. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/anomalyvfm.html))
- [Normalizing Flow Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/normalizing-flow-anomaly-detectors.md) — Anomalib models normal data distributions with conditional normalizing flows to detect anomalies in images in real time. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/cflow.html))
- [Normalizing Flow Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/normalizing-flow-detectors.md) — Anomalib transforms input data through invertible flow blocks combining affine coupling, permutation, and global affine scaling to learn complex distributions. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/components/normalizing_flows.html))
- [U-Normalizing Flow Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/normalizing-flow-detectors/u-normalizing-flow-detectors.md) — Anomalib estimates a probability distribution over normal image features using a U-shaped normalizing flow and flags regions with low likelihood as anomalies. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/fastflow.html))
- [Patch Distribution Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/patch-distribution-detectors.md) — Anomalib fits a separate Gaussian distribution to patch embeddings at each location of a pretrained CNN to detect and localize anomalies. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/padim.html))
- [Patch k-Nearest Neighbors Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/patch-k-nearest-neighbors-detectors.md) — Anomalib compares patch embeddings of test images to a memory bank of normal patches using k-nearest neighbor search to identify anomalous regions. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/anomaly_dino.html))
- [Quantized Feature Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/quantized-feature-anomaly-detectors.md) — Anomalib learns a quantized feature codebook and generates synthetic defects internally to train decoders that identify anomalies without external defect datasets. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/dsr.html))
- [Reconstruction-Based Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/reconstruction-based-anomaly-detectors.md) — Anomalib compares an input image with its reconstruction to identify anomalous regions using a discriminatively trained embedding network. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/csflow.html))
- [Reverse Distillation Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/reverse-distillation-anomaly-detectors.md) — Anomalib trains a decoder to reconstruct multi-scale features from a compressed bottleneck and scores anomalies by the reconstruction error on normal images only. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/reverse_distillation.html))
- [RGB-D Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/rgb-d-anomaly-detectors.md) — Anomalib learns mappings between 2D appearance and 3D geometry to identify anomalies in visual and depth data jointly. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/cfm.html))
- [Unsupervised Anomaly Detectors](https://awesome-repositories.com/f/data-databases/anomaly-detection-algorithms/unsupervised-anomaly-detectors.md) — Anomalib synthesizes global and local anomalies using gradient ascent on normal features to spot defects without labeled training samples. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/glass.html))
- [Sample Containers](https://awesome-repositories.com/f/data-databases/anomaly-detection/sample-containers.md) — Defines dataclasses holding input images, ground truth, masks, and predictions for each sample. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/data/dataclasses/generic.html))
- [Lightning DataModule Loaders](https://awesome-repositories.com/f/data-databases/data-pipeline-orchestration/data-engineering-pipelines/batched-data-loading/lightning-datamodule-loaders.md) — Implements Lightning DataModules for automated splitting, batching, and distributed data loading. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/data/index.html))
- [Multi-Modal Loaders](https://awesome-repositories.com/f/data-databases/vision-dataset-loading/multi-modal-loaders.md) — Anomalib loads image, video, or depth datasets for anomaly detection using pre-built dataset classes. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/data/datasets.html))

### Artificial Intelligence & ML

- [Anomaly Detection Metrics](https://awesome-repositories.com/f/artificial-intelligence-ml/anomaly-detection-metrics.md) — Computes a suite of standard metrics (AUROC, AUPR, F1, etc.) to measure anomaly detection performance. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/metrics/index.html))
- [Backbone Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/backbone-integrations.md) — Uses pretrained neural network backbones to compute deep feature representations from input data. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/models/index.html))
- [Benchmarking Suites](https://awesome-repositories.com/f/artificial-intelligence-ml/benchmarking-suites.md) — Automates hyperparameter and model grid searches across accelerators and datasets, collecting metrics in parallel across worker processes.
- [Model Performance Benchmarks](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-model-comparators/model-performance-benchmarks.md) — Runs grid searches over models, accelerators, and datasets to collect performance metrics in parallel or serial. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/pipelines/benchmark/index.html))
- [Data Preprocessing](https://awesome-repositories.com/f/artificial-intelligence-ml/data-preprocessing.md) — Anomalib applies transformations to raw images before passing them to the anomaly detection model. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/models/index.html))
- [Experiment Logging](https://awesome-repositories.com/f/artificial-intelligence-ml/experiment-logging.md) — Records training metrics, hyperparameters, and inference images to multiple experiment tracking backends. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/loggers/index.html))
- [Experiment Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/experiment-tracking.md) — Logs training metrics, hyperparameters, and model artifacts to Weights & Biases, Comet, or TensorBoard. ([source](https://cdn.jsdelivr.net/gh/open-edge-platform/anomalib@main/README.md))
- [Experiment Visualization](https://awesome-repositories.com/f/artificial-intelligence-ml/experiment-visualization.md) — Logs training parameters and outputs to loggers and generates visual plots for experiment analysis. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/index.html))
- [Feature Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-extraction.md) — Extracts intermediate feature maps from images using pretrained or custom backbone models with layer selection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/components/feature_extractors.html))
- [Anomaly Detection Pipeline Assemblers](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-extraction-pipelines/custom-feature-pipelines/anomaly-detection-pipeline-assemblers.md) — Assembles custom preprocessing, feature extraction, and classification steps into reusable anomaly detection workflows. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/pipelines/index.html))
- [Model Performance Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/model-analysis/model-performance-benchmarking.md) — Automatically collects accuracy, F1-score, and timing metrics when training and evaluating anomaly detection models. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/pipelines/benchmark/generator.html))
- [Anomaly Detection Training Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-frameworks/vision-model-training/anomaly-detection-training-workflows.md) — Trains deep neural networks on image datasets to detect visual anomalies using configurable architectures and pipelines. ([source](https://cdn.jsdelivr.net/gh/open-edge-platform/anomalib@main/README.md))
- [Training and Evaluation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/training-and-evaluation-pipelines.md) — Trains deep learning models on normal images and evaluates performance with specialized metrics.
- [Model Benchmarking Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/model-benchmarking-tools.md) — Computes metrics across multiple models via grid-search on defined configurations. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/pipelines/index.html))
- [Model Performance Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/model-performance-evaluators.md) — Computes performance metrics for anomaly detection models with stage-specific evaluation during training and inference. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/evaluation/evaluator.html))
- [Score Post-Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/anomaly-detection/anomaly-scoring/score-post-processors.md) — Converts raw anomaly scores into binary labels and heatmaps using F1-based or adaptive thresholding. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/models/post_processor.html))
- [Anomaly Detection Data Module Extensions](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-data-transform-extensions/anomaly-detection-data-module-extensions.md) — Provides base classes and data formats for integrating new anomaly detection datasets. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/data/datamodules.html))
- [Custom Post-Processing Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-post-processing-pipelines.md) — Anomalib allows defining custom post-processing logic by subclassing the base post-processor and implementing a forward method. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/models/post_processor.html))
- [Dimensionality Reduction](https://awesome-repositories.com/f/artificial-intelligence-ml/dimensionality-reduction.md) — Compresses high-dimensional feature vectors into lower-dimensional space using linear decomposition or random projection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/components/dimensionality_reduction.html))
- [Decision Threshold Calibration](https://awesome-repositories.com/f/artificial-intelligence-ml/face-detection/confidence-filtering/prediction-thresholds/decision-threshold-calibration.md) — Determines the classification threshold that maximizes the F1 score, removing the need for manual tuning. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/metrics/index.html))
- [Feature Extractor Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/feature-extractor-configurations.md) — Anomalib selects a neural network backbone from a model zoo or a custom PyTorch module to extract features for anomaly detection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/models/feature_extractors.html))
- [Feature-Based Clusterers](https://awesome-repositories.com/f/artificial-intelligence-ml/k-means-clustering/feature-based-clusterers.md) — Groups data points into clusters based on learned feature representations using GMM or K-Means algorithms. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/components/cluster.html))
- [Anomaly Visualization Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/anomaly-visualization-tools.md) — Generates visual representations of model predictions to highlight detected anomalies. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/developer/sdd.html))
- [Model Checkpointing](https://awesome-repositories.com/f/artificial-intelligence-ml/model-checkpointing.md) — Saves model weights to disk during validation or training, supporting zero-shot and few-shot scenarios. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/callbacks/index.html))
- [Anomaly-Specific Metrics](https://awesome-repositories.com/f/artificial-intelligence-ml/model-evaluation-metrics/anomaly-specific-metrics.md) — Measures model performance using anomaly-specific metrics like PRO, sPRO, and PIMO in addition to standard metrics. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/developer/sdd.html))
- [Multi-Metric Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/model-evaluation-metrics/multi-metric-orchestrators.md) — Coordinates computation of multiple evaluation metrics in a single pass for comprehensive performance reporting. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/metrics/index.html))
- [Customizable Evaluation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/model-evaluation-tools/evaluator-model-configurators/dual-engine-evaluation-pipelines/customizable-evaluation-pipelines.md) — Uses an Evaluator class to automatically update, compute, and log multiple metrics when testing a model. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/evaluation/metrics.html))
- [Hyperparameter Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/training-efficiency/hyperparameter-optimization.md) — Automates hyperparameter search for anomaly detection models using Weights & Biases or Comet.ml sweeps. ([source](https://anomalib.readthedocs.io/en/latest/markdown/get_started/anomalib.html))
- [Multi-Backend Inference Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-backend-inference-orchestration.md) — Deploys anomaly detection models using Torch, Lightning, Gradio, or OpenVINO backends. ([source](https://cdn.jsdelivr.net/gh/open-edge-platform/anomalib@main/README.md))
- [Anomaly Detection Applications](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-models/vision-language-models/anomaly-detection-applications.md) — Anomalib uses a pre-trained vision-language model and natural language prompts to compare images against reference normal images for detection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/vlm_ad.html))
- [PyTorch Model Export](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-model-export.md) — Converts trained models to PyTorch, ONNX, or OpenVINO format with optional compression and quantization. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/engine/index.html))
- [Synthetic Anomaly Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/synthetic-anomaly-generators.md) — Anomalib creates synthetic anomaly masks and augmented images using Perlin noise patterns or real anomaly source images for training. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/data/utils/synthetic.html))
- [Zero and Few-Shot Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/zero-and-few-shot-learning.md) — Detects anomalies without training data by leveraging pretrained vision-language models or reference images.

### Part of an Awesome List

- [Anomaly Segmentation](https://awesome-repositories.com/f/awesome-lists/ai/anomaly-segmentation.md) — Produces pixel-level anomaly maps that localize defects with automatic thresholding. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/image/uflow.html))
- [Video Anomaly Segmentations](https://awesome-repositories.com/f/awesome-lists/ai/anomaly-segmentation/video-anomaly-segmentations.md) — Anomalib performs few-shot unsupervised segmentation of anomalous regions in video by factorizing spatio-temporal features with low-rank constraints. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/video/index.html))
- [Video Anomaly Detection](https://awesome-repositories.com/f/awesome-lists/ai/video-anomaly-detection.md) — Anomalib identifies anomalous events in video streams using attribute-based representations that provide accurate and interpretable detections. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/video/index.html))
- [Attribute-Based Video Anomaly Detections](https://awesome-repositories.com/f/awesome-lists/ai/video-anomaly-detection/attribute-based-video-anomaly-detections.md) — Anomalib extracts regions of interest from video frames and computes attribute-based representations to identify anomalous events. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/models/index.html))
- [Anomaly Detection Data Structures](https://awesome-repositories.com/f/awesome-lists/data/data-validation-and-anomaly-detection/anomaly-detection-data-structures.md) — Defines typed dataclasses for image, video, and depth data used in anomaly detection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/data/dataclasses.html))
- [Anomaly Detection Data Containers](https://awesome-repositories.com/f/awesome-lists/devtools/type-checking/dataclass-field-type-validators/anomaly-detection-data-containers.md) — Defines typed dataclasses for anomaly detection samples with automatic field validation.

### Business & Productivity Software

- [Quality Defect Detection](https://awesome-repositories.com/f/business-productivity-software/manufacturing-planning-tools/quality-defect-detection.md) — Detects defects and irregularities in manufacturing images using deep learning models for quality control.
- [Platforms](https://awesome-repositories.com/f/business-productivity-software/manufacturing-planning-tools/quality-defect-detection/platforms.md) — Ships a no-code web app and CLI for training and deploying anomaly detection models on manufacturing visual data.

### Development Tools & Productivity

- [CLI Automation Tools](https://awesome-repositories.com/f/development-tools-productivity/cli-automation-tools.md) — Provides a CLI to run training, evaluation, and inference without writing scripts. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/index.html))
- [ML Experiment Loggers](https://awesome-repositories.com/f/development-tools-productivity/custom-loggers/ml-experiment-loggers.md) — Logs training metrics and configurations to TensorBoard, Weights & Biases, or Comet.ml through Lightning loggers. ([source](https://anomalib.readthedocs.io/en/latest/markdown/get_started/anomalib.html))
- [Stage-Specific Batch Transforms](https://awesome-repositories.com/f/development-tools-productivity/batch-processing-pipelines/inference-batching/stage-specific-batch-transforms.md) — Applies separate transform sets to data batches for each pipeline stage during training and inference. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/pre_processing/index.html))
- [CLI Configuration Files](https://awesome-repositories.com/f/development-tools-productivity/cli-configuration-files.md) — Configures experiments via command-line arguments and YAML/JSON configuration files. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/cli/index.html))
- [Pipeline Execution Interfaces](https://awesome-repositories.com/f/development-tools-productivity/headless-execution-environments/cli-execution/pipeline-execution-interfaces.md) — Orchestrates the complete anomaly detection workflow through a command-line interface. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/developer/sdd.html))

### DevOps & Infrastructure

- [Modular Frameworks](https://awesome-repositories.com/f/devops-infrastructure/automated-analysis-pipelines/multi-stage-analysis-pipelines/anomaly-detection-pipelines/modular-frameworks.md) — Provides a modular framework for building custom anomaly detection pipelines with interchangeable components.
- [Model Inference Deployment](https://awesome-repositories.com/f/devops-infrastructure/deployment-management/model-inference-deployment.md) — Exports models to OpenVINO IR and provides inference tools for production anomaly detection. ([source](https://anomalib.readthedocs.io/en/latest/))
- [Visual Anomaly Detection Toolkits](https://awesome-repositories.com/f/devops-infrastructure/model-conversion/pytorch/visual-anomaly-detection-toolkits.md) — Provides a library of deep learning models and tools for detecting visual defects in images and video using PyTorch.
- [Anomaly Detection Pipelines](https://awesome-repositories.com/f/devops-infrastructure/automated-analysis-pipelines/multi-stage-analysis-pipelines/anomaly-detection-pipelines.md) — Executes multi-stage pipelines with sequential and parallel job stages for anomaly detection. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/pipelines/runners/index.html))
- [Model Export Formats](https://awesome-repositories.com/f/devops-infrastructure/deployment-management/model-export-formats.md) — Converts trained models to ONNX, OpenVINO IR, or PyTorch for production deployment. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/cli/index.html))
- [No-Code Training Interfaces](https://awesome-repositories.com/f/devops-infrastructure/web-deployment-pipelines/no-code-training-interfaces.md) — Provides a no-code web application for training and deploying anomaly detection models. ([source](https://cdn.jsdelivr.net/gh/open-edge-platform/anomalib@main/README.md))

### Graphics & Multimedia

- [Model Export Pipelines](https://awesome-repositories.com/f/graphics-multimedia/video-converters/multi-format-exporters/multi-format-asset-exports/model-export-pipelines.md) — Exports trained anomaly detection models to ONNX, OpenVINO, and PyTorch for edge deployment.
- [Real-Time Model Inference on Frames](https://awesome-repositories.com/f/graphics-multimedia/video-frame-processing/real-time-model-inference-on-frames.md) — Deploys trained models for low-latency inference on edge devices using ONNX and OpenVINO.
- [Edge Deployments](https://awesome-repositories.com/f/graphics-multimedia/video-frame-processing/real-time-model-inference-on-frames/edge-deployments.md) — Exports models to OpenVINO and performs real-time anomaly detection on streaming data at the edge. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/developer/sdd.html))

### Software Engineering & Architecture

- [Anomaly Score Post-Processors](https://awesome-repositories.com/f/software-engineering-architecture/modular-architecture-frameworks/anomaly-score-post-processors.md) — Provides configurable thresholding to convert raw anomaly scores into interpretable heatmaps and binary masks.
- [Anomaly Detection Algorithm Plugins](https://awesome-repositories.com/f/software-engineering-architecture/software-architecture/architectural-patterns/plugin-module-systems/modular-plugin-architectures/plugin-based-architectures/plugin-based-architectures/anomaly-detection-algorithm-plugins.md) — Implements anomaly detection algorithms as pluggable LightningModules with a standardized interface.

### Testing & Quality Assurance

- [Model Evaluation](https://awesome-repositories.com/f/testing-quality-assurance/model-testing/model-evaluation.md) — Evaluates trained anomaly detection models on test datasets and reports computed performance metrics. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/reference/cli/index.html))

### User Interface & Experience

- [Test Result Visualizers](https://awesome-repositories.com/f/user-interface-experience/custom-ui-components/test-result-visualizers.md) — Generates visual overlays of anomaly maps and segmentation masks during test and predict steps. ([source](https://anomalib.readthedocs.io/en/latest/markdown/guides/how_to/visualization/visualize_image.html))