145 Open Source Interpretability Software Projects
Free and open source interpretability code projects including engines, APIs, generators, and tools.
Awesome Production Machine Learning 10782 ⭐
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
Lucid 4359 ⭐
A collection of infrastructure and tools for research in neural network interpretability.
Awesome Machine Learning Interpretability 2447 ⭐
A curated list of awesome machine learning interpretability resources.
Ad_examples 735 ⭐
A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.
Interpretable_machine_learning_with_python 587 ⭐
Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.
Neural Backed Decision Trees 510 ⭐
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Pyss3 230 ⭐
A Python package implementing a new interpretable machine learning model for text classification (with visualization tools for Explainable AI :octocat:)
Visual Attribution 134 ⭐
Pytorch Implementation of recent visual attribution methods for model interpretability
Visualizing Cnns For Monocular Depth Estimation 118 ⭐
official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"
Scalaconsultants Aspect Based Sentiment Analysis 324 ⭐
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
Hierarchical Dnn Interpretations 101 ⭐
Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Cxplain 99 ⭐
Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
Torch Cam 643 ⭐
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)
Explainx 280 ⭐
Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.
Summit 91 ⭐
🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
Interpretability Implementations Demos 438 ⭐
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Arabiaweather Athena 61 ⭐
Automatic equation building and curve fitting. Runs on Tensorflow. Built for academia and research.
Interpretability By Parts 103 ⭐
Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Deep Explanation Penalization 93 ⭐
Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Cnn Interpretability 95 ⭐
🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
Neuron Importance Zsl 56 ⭐
[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance
Qaconv 120 ⭐
Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting
Reverse Engineering Neural Networks 91 ⭐
A collection of tools for reverse engineering neural networks.
Spine 44 ⭐
Code for SPINE - Sparse Interpretable Neural Embeddings. Jhamtani H.*, Pruthi D.*, Subramanian A.*, Berg-Kirkpatrick T., Hovy E. AAAI 2018
Representer_point_selection 55 ⭐
code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018
Adversarial Robustness Public 44 ⭐
Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
Modeloriented Live 34 ⭐
Local Interpretable (Model-agnostic) Visual Explanations - model visualization for regression problems and tabular data based on LIME method. Available on CRAN
Mmn 38 ⭐
Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
Contrastiveexplanation 38 ⭐
Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University
Movie Recommendation Netflix 32 ⭐
🔮Trying to find the best movie to watch on Netflix can be a daunting. Case Study for Recommendation System of movies in Netflix.🔧
Symbolic Metamodeling 36 ⭐
Codebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.
Neural Ir Explorer 27 ⭐
Neural-IR-Explorer: A Content-Focused Tool to Explore Neural Re-Ranking Results
Diabetes_use_case 22 ⭐
Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/
Xai Iml Sota 42 ⭐
Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Disentangled Attribution Curves 20 ⭐
Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"
Hc_ml 20 ⭐
Slides, videos and other potentially useful artifacts from various presentations on responsible machine learning.
Awesome Adversarial Interpretable Machine Learning 121 ⭐
💡 Adversarial attacks on model explanations, and evaluation approaches
Oncotext 19 ⭐
OncoText is an information extraction service for breast pathology reports. It supports over 20 categories including DCIS, includes pretrained models, and supports flexible addition of new categories, new training data, and parsing new reports.
Feature Vis Yolov3 15 ⭐
Feature visualization tool for YOLOv3, a real-time objection detection algorithm using a deep convolutional network with a Darknet backbone. Visualizes performance attributes via saliency maps to identify how features in the input pixel space influence our network’s predictions in terms of classification and localization
Interpretable Ml 17 ⭐
Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.
Working Women 12 ⭐
Code for the paper 'Working Women and Caste in India' (ICLR 2019 AI for Social Good Workshop)
Egocnn 14 ⭐
Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)
Machine Learning Summer Schools 13 ⭐
Curated materials for different machine learning related summer schools
Class_selectivity_index 11 ⭐
On the importance of single directions for generalization(Morcos et al, ICLR 2018)
Sklearn_explain 12 ⭐
Model explanation provides the ability to interpret the effect of the predictors on the composition of an individual score.
Lime Interpretable Ml 10 ⭐
An example of how the LIME algorithm can be used to provide real-world insight into the decision processes of a 'black-box' machine learning algorithm - in this case a Radom Forest regressor.
Transformer_anatomy 14 ⭐
Official Pytorch implementation of (Roles and Utilization of Attention Heads in Transformer-based Neural Language Models), ACL 2020
Laundryml 14 ⭐
Code for our paper "Fairwashing: the risk of rationalization" (https://arxiv.org/abs/1901.09749) accepted at ICML 2019.
Pytorch Grad Cam 4041 ⭐
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
Transformers Interpret 544 ⭐
Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Decision Forests 391 ⭐
A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.
Transformer Mm Explainability 289 ⭐
[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.