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

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Python bindings for FFmpeg - with complex filtering support

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Turn your Python application into an Android APK

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

Count the MACs / FLOPs of your PyTorch model.

An easy to use PyTorch to TensorRT converter

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

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Visual localization made easy with hloc

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

Sandbox for training deep learning networks

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

The devkit of the nuScenes dataset.

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

Code base of the BEVDet series .

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Reference implementations of MLPerf® inference benchmarks

[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

Image Signal Processor

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

A full Python implementation for real car surround view system

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images