This is a great place in our repo where you can try some capabilities and functions you can achieve with Anomalib. First follow the installation guide and then explore the notebooks that it offers to you.
To install Python, Git and other required tools, OpenVINO Notebooks repository provides a good documentation. For more details please refer to the Installation Guide.
| Windows | Ubuntu | macOS | Red Hat | CentOS | Azure ML | Docker | Amazon SageMaker |
|---|
The notebooks are organized in a logical learning progression:
| Section | Directory | Description |
|---|---|---|
| Getting Started | 01_getting_started/ |
Basic training and inference workflows |
| Data | 02_data/ |
Working with datasets, datamodules, and data utilities |
| Models | 03_models/ |
Training and using different anomaly detection models |
| Metrics | 04_metrics/ |
Evaluation metrics and performance analysis |
| Loggers | 05_loggers/ |
Logging and experiment tracking |
| Visualization | 06_visualization/ |
Visualizing results and anomaly maps |
| Deployment | 07_deployment/ |
Model optimization and deployment |
Start with the Getting Started section to learn the basics, then progress through the sections based on your needs:
- 01_getting_started - Learn basic anomalib workflows
- 02_data - Understand data handling and preprocessing
- 03_models - Explore different anomaly detection models
- 04_metrics - Evaluate model performance
- 05_loggers - Track experiments and results
- 06_visualization - Visualize and interpret results
- 07_deployment - Deploy models for production use
Each section contains its own README with detailed descriptions and direct links to Colab notebooks.