Stars
The free and open source API to generate memes.
A platform for managing machine learning experiments
A Dataset of Python Challenges for AI Research
Real-time face swap for PC streaming or video calls
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
😈Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness
Attributing predictions made by the Inception network using the Integrated Gradients method
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
A web application for renters in New York City to access relevant but hard-to-acquire information on the neighborhoods and buildings that they are interested in renting in.
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
Fit interpretable models. Explain blackbox machine learning.
Code for the paper "Jukebox: A Generative Model for Music"
Evaluating recurrent neural networks on predicting subject-verb agreement dependencies
Gradient based receptive field estimation for Convolutional Neural Networks
Visualizations for machine learning datasets
Understanding Deep Networks via Extremal Perturbations and Smooth Masks
A game theoretic approach to explain the output of any machine learning model.
PAIR.withgoogle.com and friend's work on interpretability methods
BertViz: Visualize Attention in Transformer Models
Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).
Code for a web demo of Plan, Write, and Revise: a neural system for interactive open-domain story generation
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.