101 Open source projects that are alternatives of or similar to Interpretability By Parts

DCGAN Implementation using PyTorch in both C++ and Python

🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.

Pytorch implementation of β-VAE

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

Federated Learning Library: https://fedml.ai

Code for SPINE - Sparse Interpretable Neural Embeddings. Jhamtani H.*, Pruthi D.*, Subramanian A.*, Berg-Kirkpatrick T., Hovy E. AAAI 2018

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

A collection of infrastructure and tools for research in neural network interpretability.

Fit interpretable models. Explain blackbox machine learning.

Concept Bottleneck Models, ICML 2020

Interpretability Methods for tf.keras models with Tensorflow 2.x

[CVPR2020] Adversarial Latent Autoencoders

Text classification models. Used a submodule for other projects.

Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/

Visualization toolkit for neural networks in PyTorch! Demo -->

A library for finding knowledge neurons in pretrained transformer models.

A large-scale face dataset for face parsing, recognition, generation and editing.

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking

Implementation of VAE and Style-GAN Architecture Achieving State of the Art Reconstruction

Algorithms for monitoring and explaining machine learning models

Code for "Free-Lunch Saliency via Attention in Atari Agents"

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

moDel Agnostic Language for Exploration and eXplanation

Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"

💡 A curated list of adversarial attacks on model explanations

Pytorch implementation of conditional Generative Adversarial Networks (cGAN) and conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for MNIST dataset

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.

Human-explainable AI.

🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease

Study Friendly Implementation of DCGAN in Tensorflow

XAI - An eXplainability toolbox for machine learning

A lightweight implementation of removal-based explanations for ML models.

General Interpretability Package

Towards Understanding Deep Learning Representations via Interactive Experimentation

Interesting resources related to XAI (Explainable Artificial Intelligence)

[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance

Modified h5tool.py make user getting celeba-HQ easier

For calculating global feature importance using Shapley values.

Public facing deeplift repo

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Codebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.

official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"

Code for the TCAV ML interpretability project

Learning to Avoid Errors in GANs by Input Space Manipulation (Code for paper)

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Python package to visualize and cluster partial dependence.

H2O.ai Machine Learning Interpretability Resources

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)

Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.

A collection of tools for reverse engineering neural networks.

Automatic equation building and curve fitting. Runs on Tensorflow. Built for academia and research.

[ICCV 2017] Torch code for Grad-CAM

Experiments for understanding disentanglement in VAE latent representations