model-interpretability 开源项目推荐（217 个）

kserve /kserve

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

kitops-ml /kitops

来自 CNCF 的开源 DevOps 工具，用于将 AI/ML 模型、数据集、代码和配置打包并版本化为 OCI Artifact。

chrishayuk /larql

Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.

yizt /Grad-CAM.pytorch

pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络; 同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图; 欢迎试用、关注并反馈问题...

yulongwang12 /visual-attribution

Pytorch Implementation of recent visual attribution methods for model interpretability

rehmanzafar /xai-iml-sota

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

TannerGilbert /Model-Interpretation

Overview of different model interpretability libraries.

kapelner /ICEbox

R tools for Individual Conditional Expectation plots, derivative ICE, partial dependence, and model-interpretability diagnostics.

Tramac /pytorch-cam

Class Activation Map (CAM) Visualizations in PyTorch.

AmanPriyanshu /GPT-OSS-MoE-ExpertFingerprinting

ExpertFingerprinting: Behavioral Pattern Analysis and Specialization Mapping of Experts in GPT-OSS-20B's Mixture-of-Experts Architecture

Hellisotherpeople /Active-Explainable-Classification

A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

evanseitz /squid-nn

surrogate quantitative interpretability for deepnets

pranoy-panda /Causal-Feature-Subset-Selection

Official repository for the paper "Instance-wise Causal Feature Selection for Model Interpretation" (CVPRW 2021)

AmirhosseinHonardoust /Car-Value-Decomposition-Theory

This article explores the theory behind explainable car pricing using value decomposition, showing how machine learning models can break a predicted price into intuitive components such as brand premium, age depreciation, mileage influence, condition effects, and transmission or fuel-type adjustments.

zphang /saliency_investigation

Code for "Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability" (https://arxiv.org/abs/2010.09750)

aimaster-dev /default_loan_prediction

该项目利用人工智能和机器学习模型自动化银行信用风险评估，预测贷款违约情况。它通过预测分析、模型评估、可解释性（SHAP）和部署准备，简化了信用流程。

juliotorrest /yield_aeroponics

AI to Predict Yield in Aeroponics

Ankit-Kumar-Saini /Coursera_TensorFlow_Advanced_Techniques_Specialization

Used the Functional API to built custom layers and non-sequential model types in TensorFlow, performed object detection, image segmentation, and interpretation of convolutions. Used generative deep learning including Auto Encoding, VAEs, and GANs to create new content.

Shuyib /chronic-kidney-disease-kaggle

Using machine learning models to predict if patients have chronic kidney disease based on a few features. The results of the models are also interpreted to make it more understandable to health practitioners.

nyuvis /ml-interview-study

Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs