1 रिपॉजिटरी
Awesome GitHub RepositoriesAttribution Computation Distribution
Distributing attribution algorithm calculations across multiple processors, machines, or GPUs to speed up processing.
Distinct from Distributed Computing: Distinct from Distributed Computing: specifically for distributing attribution computations rather than general distributed processing.
Explore 1 awesome GitHub repository matching data & databases · Attribution Computation Distribution. Refine with filters or upvote what's useful.
Awesome Attribution Computation Distribution GitHub Repositories
AI के साथ बेहतरीन रिपॉजिटरी खोजें।हम AI का उपयोग करके सबसे सटीक रिपॉजिटरी खोजेंगे।
- pytorch/captum
pytorch/captum
5,652GitHub पर देखेंCaptum 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
Distributes attribution algorithm calculations across multiple processors or GPUs to speed up processing.
Python
