iml 开源项目推荐（69 个）

interpretml /interpret

适合可解释的模型。解释黑匣子机器学习。

ModelOriented /DALEX

用于探索与解释的模型无关语言

jphall663 /interpretable_machine_learning_with_python

用于训练可解释机器学习模型、解释机器学习模型，以及调试机器学习模型以提升准确性、减少歧视并增强安全性的技术示例。

h2oai /mli-resources

H2O.ai 机器学习可解释性资源

hbaniecki /adversarial-explainable-ai

对解释的对抗攻击及如何防御

ModelOriented /modelStudio

📍 Interactive Studio for Explanatory Model Analysis

scu-zjz /IMDLBenCo

[NeurIPS'24 Spotlight] A comprehensive benchmark & codebase for Image manipulation detection/localization.

givasile /effector

Effector - a Python package for global and regional effect methods

adsorgcn /WorkBuddy

iLang 专家与技能的 GitHub 安装源，海外版 WorkBuddy 可直接装：公众号爆文结构专家 v2.0（素材进稿子出，12 项自查，内置去 AI 味）· iLang experts & skills for WorkBuddy, installable from GitHub

12wang3 /rrl

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classification"

ModelOriented /treeshap

Compute SHAP values for your tree-based models using the TreeSHAP algorithm

automl /DeepCAVE

An interactive framework to visualize and analyze your AutoML process in real-time.

pbiecek /breakDown

Model Agnostics breakDown plots

nredell /ShapML.jl

A Julia package for interpretable machine learning with stochastic Shapley values

ModelOriented /iBreakDown

Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)

rehmanzafar /xai-iml-sota

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

nredell /shapFlex

An R package for computing asymmetric Shapley values to assess causality in any trained machine learning model

dddb11 /MVSS-Net

Unofficial implementation of MVSS-Net (ICCV 2021) with Pytorch including training code.

ModelOriented /live

Local Interpretable (Model-agnostic) Visual Explanations - model visualization for regression problems and tabular data based on LIME method. Available on CRAN

pyartemis /artemis

A Python package with explanation methods for extraction of feature interactions from predictive models