awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
jacobgil avatar

jacobgil/vit-explain

0
View on GitHub↗
1,090 stele·108 fork-uri·Python·MIT·5 vizualizări

Vit Explain

Vit-explain este un framework de diagnosticare conceput pentru a interpreta procesele de luare a deciziilor ale modelelor de tip vision transformer. Funcționează ca un toolkit pentru inspectarea stărilor interne ale modelului, permițând utilizatorilor să mapeze atenția vizuală și să analizeze modul în care caracteristicile specifice ale imaginii influențează rezultatele clasificării.

Proiectul se distinge prin furnizarea unei interpretări post-hoc a modelului, care permite analiza rețelelor neuronale antrenate fără a necesita modificări arhitecturale sau reantrenare. Utilizează tehnici precum extragerea de caracteristici bazată pe hook-uri pentru a intercepta activările interne în timpul trecerii înainte (forward pass), alături de metode precum transformer attention rollout și layer-wise relevance propagation pentru a urmări fluxul de informații de la input la output.

Prin generarea de hărți de căldură (heatmaps) care urmăresc fluxul de atenție și distribuția ponderilor, framework-ul vizualizează care pixeli și tipare specifice conduc predicțiile unui model. Suportă explicații specifice clasei prin filtrarea hărților de atenție cu gradienți ai clasei țintă, oferind un utilitar de diagnosticare pentru depanarea modelelor de deep learning și identificarea elementelor vizuale care contribuie la rezultatele clasificării.

Features

  • Deep Learning Interpretability - Analyzes neural network decision-making processes by mapping visual attention weights and gradients to input image regions.
  • Transformer Explainability - Analyzes how vision transformer models process visual data by generating heatmaps that track attention flow across image regions.
  • Attention Rollout Techniques - Aggregates attention maps across multiple layers by recursively multiplying weight matrices to trace the flow of information.
  • Attention Visualizations - Generates heatmaps that track the flow of attention across image regions to reveal model processing priorities.
  • Computer Vision Model Debugging - Visualizes internal decision-making processes by highlighting specific pixels and patterns that drive classification results.
  • Internal Activation Hooks - Intercepts internal tensor activations during the forward pass to capture intermediate attention maps without modifying model architecture.
  • Attribution Gradients - Calculates feature importance by backpropagating gradients from target classification outputs to input image patches.
  • Relevance Propagation Methods - Distributes classification scores backward through network layers to identify which specific input pixels contributed most to the final prediction.
  • Class-Specific Explainers - Filters attention maps with target class gradients to isolate visual elements contributing to specific classification outcomes.
  • Transformer Explainability Tools - Provides diagnostic utilities for visualizing attention maps and gradients to interpret vision transformer classification features.
  • Architecture Interpretation - Analyzes trained model weights and gradients to provide visual explanations without requiring retraining or architectural changes.

Istoric stele

Graficul istoricului de stele pentru jacobgil/vit-explainGraficul istoricului de stele pentru jacobgil/vit-explain

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Colecții curatoriate care includ Vit Explain

Colecții selectate manual în care apare Vit Explain.
  • Instrumente pentru interpretarea modelelor de Machine Learning

Întrebări frecvente

Ce face jacobgil/vit-explain?

Vit-explain este un framework de diagnosticare conceput pentru a interpreta procesele de luare a deciziilor ale modelelor de tip vision transformer. Funcționează ca un toolkit pentru inspectarea stărilor interne ale modelului, permițând utilizatorilor să mapeze atenția vizuală și să analizeze modul în care caracteristicile specifice ale imaginii influențează rezultatele clasificării.

Care sunt principalele funcționalități ale jacobgil/vit-explain?

Principalele funcționalități ale jacobgil/vit-explain sunt: Deep Learning Interpretability, Transformer Explainability, Attention Rollout Techniques, Attention Visualizations, Computer Vision Model Debugging, Internal Activation Hooks, Attribution Gradients, Relevance Propagation Methods.

Care sunt câteva alternative open-source pentru jacobgil/vit-explain?

Alternativele open-source pentru jacobgil/vit-explain includ: cdpierse/transformers-interpret — Transformers-interpret is a diagnostic library designed for the interpretability of transformer-based machine learning… jacobgil/pytorch-grad-cam — This project is a computer vision explainable AI library and framework for PyTorch, providing a suite of tools to… transformerlensorg/transformerlens — TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned… christophm/interpretable-ml-book — This project is a comprehensive educational resource and technical manual focused on interpretable machine learning… tingsongyu/pytorch_tutorial — This project is a comprehensive collection of educational examples and reference implementations for building vision… tingsongyu/pytorch-tutorial-2nd — This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It…

Alternative open-source pentru Vit Explain

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Vit Explain.
  • cdpierse/transformers-interpretAvatar cdpierse

    cdpierse/transformers-interpret

    1,412Vezi pe GitHub↗

    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

    Jupyter Notebookcaptumcomputer-visiondeep-learning
    Vezi pe GitHub↗1,412
  • jacobgil/pytorch-grad-camAvatar jacobgil

    jacobgil/pytorch-grad-cam

    12,893Vezi pe GitHub↗

    This project is a computer vision explainable AI library and framework for PyTorch, providing a suite of tools to visualize and audit the internal decision-making processes of deep neural networks. It serves as a neural network attribution tool and debugging utility to identify which image regions drive model predictions. The library is distinguished by its support for both gradient-based and gradient-free attribution methods, allowing for the generation of visual heatmaps and attribution maps without requiring modifications to the original model source code. It further differentiates itself

    Python
    Vezi pe GitHub↗12,893
  • transformerlensorg/transformerlensAvatar TransformerLensOrg

    TransformerLensOrg/TransformerLens

    3,098Vezi pe GitHub↗

    TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned algorithms within large language models. It provides a standardized framework for wrapping diverse transformer architectures, allowing researchers to extract, manipulate, and analyze internal activations and weights through a consistent interface. The project distinguishes itself through a comprehensive system of activation hooks that can capture, patch, and ablate internal tensors during the forward pass. It includes specialized utilities for decomposing fused projections, material

    Python
    Vezi pe GitHub↗3,098
  • christophm/interpretable-ml-bookAvatar christophM

    christophM/interpretable-ml-book

    5,317Vezi pe GitHub↗

    This project is a comprehensive educational resource and technical manual focused on interpretable machine learning and explainable AI. It serves as a textbook and reference for implementing techniques that make complex machine learning models transparent and understandable to humans. The resource provides guidance on both building inherently transparent models, such as decision trees and sparse linear models, and applying post-hoc explanation methods to black-box systems. It details specific methodologies for quantifying feature importance, generating rationales for individual predictions, a

    Jupyter Notebook
    Vezi pe GitHub↗5,317
Vezi toate cele 20 alternative pentru Vit Explain→