lem89757
Follow
Stars
MiDaS（Multiple Depth Estimation Accuracy with Single Network）单目深度估计，部署 rk3588。
10000 fps 🚀 for 360 Surround-View CUDA Solution
The C++ code demo for surround view of car
Yolov5 inference on NVDec hardware decoder
A large number of cuda/tensorrt cases . 大量案例来学习cuda/tensorrt
基于rknn的官方Android项目rknn_yolov5_android_apk_demo进行修改，部署人脸检测模型retinaface和106人脸关键点检测模型，支持实时人脸检测。支持rk356x和rk3588设备npu推理。
基于RK3588的边缘预警项目（C++）。 采用Yolov7算法，通过读取输入视频源（RTSP、USB摄像头等），经过自创轻量级目标跟踪算法去重检测，将告警信息实时通过HTTP接口推送，同时将视频源进行转发并利用RTMP协议推送。
rk3588实现车辆虚线变道不打灯行为检测
rk3588 various solutions for reading camera and video files
Real-time Face and Iris Landmarks Detection using C++
rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.
🚀 免费订阅地址，🚀 免费节点，🚀 6小时更新一次，共享节点，节点质量高可用，完全免费。免费clash订阅地址，免费翻墙、免费科学上网、免费梯子、免费ss/v2ray/trojan节点、谷歌商店、翻墙梯子。注意：目前进入官网需开启代理。
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
SLMaster is a relatively complete open-source Structured Light 3D camera software. You can use it to complete a series of operations including calibration, stripe encoding, 3D reconstruction, and p…
跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : ) 。**VideoPipe下一版本正在开发中，在保证跨平台、易上手的前提下，预计性能直逼deepstream等各硬件平台官方框架**。
Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
C++ implementation of BoT-SORT MOT algorithm with Re-ID and Camera Motion Compensation
Converting YOLOv8 models to TensorRT of FP16 and INT8
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695
[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
C++ library based on tensorrt integration