How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Algorithms for outlier, adversarial and drift detection
The main features of seldonio/alibi-detect are: Drift Detection, Explainable AI Libraries, Model Evaluation, Monitoring and Drift, Data Quality and Validation, Data Validation and Anomaly Detection, Developer Tools.
Projects with overlapping indexed features include: torchdrift/torchdrift — Drift Detection for your PyTorch Models. tensorflow/data-validation — Library for exploring and validating machine learning data. pydantic/pydantic — Pydantic is a data validation and serialization library that enforces schema constraints and performs type conversion… microsoft/tensorwatch — Debugging, monitoring and visualization for Python Machine Learning and Data Science. raghakot/keras-vis — keras-vis is a high-level toolkit for visualizing and debugging your trained keras neural net models. Currently… pytorch/captum — Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and…
Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in
Debugging, monitoring and visualization for Python Machine Learning and Data Science
Pydantic is a data validation and serialization library that enforces schema constraints and performs type conversion on complex data structures. It utilizes standard Python type annotations to define data models, allowing developers to establish structured schemas that automatically enforce business rules and constraints without the need for custom domain-specific languages. The library distinguishes itself by transforming high-level model definitions into optimized code during initialization to minimize runtime overhead. It supports recursive validation for nested data structures and employ
