Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

TensorRT deployment for CenterPoint Lidar Detection Model.

A full Python implementation for real car surround view system

音视频(H264/H265/AAC)封装、解封装、编解码pipeline，支持NVIDIA、昇腾DVPP硬编解码

NVIDIA DeepStream SDK 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

SuperPoint and SuperGlue with TensorRT. Deploy with C++.

SuperPoint-SuperGlue-ONNX

Efficient neural feature detector and descriptor

FFmpeg with async and zero-copy Rockchip MPP & RGA support

a simple rtsp server which can pull stream from a camera with "rtsp://", save the video as ts stream, and supply a rtsp server both realtime stream and the local video,

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

CGO bindings to RKNN-Toolkit2 to perform Inferencing in Go on Rockchip NPU

Using OpenCV pull RTSP and using FFmpeg push a new RTSP

Extra Gstreamer Plugins for RockChip SDK

Extra Gstreamer Plugins for RockChip SDK

TensorRT+YOLO系列的 多路 多卡 多实例 并行视频分析处理案例

A new tensorrt integrate. Easy to integrate many tasks

Stable Diffusion Installation on Intel Arc A770 Tutorial

Grok open release

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

NVIDIA TensorRT deployment of Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.

TensorRT implementation of Depth-Anything V1, V2

Efficient vision foundation models for high-resolution generation and perception.

将server端opencv读取的视频帧通过gstreamer推流到rtmp服务器上。