The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Data and code behind the articles and graphics at FiveThirtyEight

Playing Pokemon Red with Reinforcement Learning

Book about interpretable machine learning

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

A data visualization curriculum of interactive notebooks.

Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

Misc data visualization projects, examples, and demos: mostly Python (pandas + matplotlib) and JavaScript (leaflet).

Spit shine for Jupyter notebooks 🧽✨

Land Cover Mapping

Find and fix bugs in natural language machine learning models using adaptive testing.

Physical adversarial attack for fooling the Faster R-CNN object detector

Materials Knowledge System in Python

Code for training and testing deep learning based land cover models.

https://pair.withgoogle.com/explorables/

Interactively and visually explore large-scale image datasets used in machine learning using treemaps. VIS 2022

An idyll post all about dimensionality reduction.

Automatic Training Data Generation with Affinity Coding

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

Summarizing Entertainment Video Using Color and Dialogue

Semantic Regex

Interactive VQ-VAE (Vector-Quantized Variational Autoencoder) in the browser

Materials for running the usability study for the technical paper, "Managing Messes in Computational Notebooks".