openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

The official Meta Llama 3 GitHub site

Python sample codes and textbook for robotics algorithms.

State-of-the-art 2D and 3D Face Analysis Project

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Graph Neural Network Library for PyTorch

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Datasets, Transforms and Models specific to Computer Vision

End-to-End Object Detection with Transformers

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Matplotlib styles for scientific plotting

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

Object detection, 3D detection, and pose estimation using center point detection:

OpenMMLab's next-generation platform for general 3D object detection.

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

The most powerful local music generation model that outperforms most commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Learning to See in the Dark. CVPR 2018

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

A highly efficient implementation of Gaussian Processes in PyTorch

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

A minimalist environment for decision-making in autonomous driving