Stars
Open and efficient video watermarking
🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Flash Attention in ~100 lines of CUDA (forward pass only)
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
Hackable and optimized Transformers building blocks, supporting a composable construction.
Python library for Multi-Armed Bandits
Python package for creating and visualizing interactive network graphs.
A game theoretic approach to explain the output of any machine learning model.
🎵 A repository for manually annotating files to create labeled acoustic datasets for machine learning.
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
TensorFlow-based neural network library
Source code for models described in the paper "ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio" (https://arxiv.org/abs/2104.11587)
A data augmentations library for audio, image, text, and video.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
Fast Python Collaborative Filtering for Implicit Feedback Datasets
Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch
Best Practices on Recommendation Systems
💃 Real-time single person pose estimation for Android and iOS.
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
Make huge neural nets fit in memory