A high-performance runtime framework for modern robotics.

A GStreamer Deep Learning Inference Framework

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Production-ready platform for agentic workflow development.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

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

Code base of the BEVDet series .

Eclipse Cyclone DDS project

Eclipse iceoryx™ - true zero-copy inter-process-communication

The repository containing tools and information about the WoodScape dataset.

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

Fast, easy and reliable testing for anything that runs in a browser.

Two-stage CenterNet

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

RepVGG: Making VGG-style ConvNets Great Again

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

PyTorch1.0 深度学习：60分钟入门与实战（Deep Learning with PyTorch: A 60 Minute Blitz 中文翻译与学习）

A Keras implementation of YOLOv4 (Tensorflow backend)

Convolutional Neural Networks

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Caffe: a fast open framework for deep learning.

Gluon CV Toolkit

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现，项目已得到李沐老师的认可

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow

OpenMMLab Detection Toolbox and Benchmark

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.