2 个仓库
Awesome GitHub RepositoriesCustom Attribution Algorithm Frameworks
Generic base classes and hooks for implementing, benchmarking, and sharing new attribution methods.
Distinct from Model Interpretability Frameworks: Distinct from Model Interpretability Frameworks: focuses on the extensibility mechanism for adding new attribution algorithms, not the full interpretability workflow.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Custom Attribution Algorithm Frameworks. Refine with filters or upvote what's useful.
Awesome Custom Attribution Algorithm Frameworks GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- pytorch/captum
pytorch/captum
5,652在 GitHub 上查看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
Provides a generic framework for implementing, benchmarking, and sharing new attribution methods.
Python - cdpierse/transformers-interpret
cdpierse/transformers-interpret
1,412在 GitHub 上查看Transformers-interpret is a diagnostic library designed for the interpretability of transformer-based machine learning models. It functions as an attribution framework that quantifies the contribution of individual input tokens to a model's final predictions, allowing users to audit decision patterns and debug natural language processing tasks. The library utilizes gradient-based analysis and hook-based introspection to trace how specific input features influence model outputs. By mapping abstract numerical attribution scores back to human-readable linguistic units, it provides a clear view o
Provides a framework-agnostic engine that decouples attribution logic from specific transformer model architectures.
Jupyter Notebookcaptumcomputer-visiondeep-learning
