LightSeq: A High Performance Library for Sequence Processing and Generation

[ECCV'24] Kalman-Inspired Feature Propagation for Video Face Super-Resolution

The RaftLib C++ library, streaming/dataflow concurrency via C++ iostream-like operators

LLM training in simple, raw C/CUDA

A generative speech model for daily dialogue.

This project offers a clear explanation of flv.js, a JavaScript library for FLV media files, through code analysis and a simple online demo.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

🔥 作者：常炎隆(Author: ChangYanlong):HEVC/H.265 网页直播/点播播放器 支持硬解！ 支持H.265的HttpFLV/HLS/MP4/TS/FLV/M3U8/Websocket播放。 🔥 A HEVC/H.265 Web Player, Support hard-decoding! for LIVE/VOD stream. Support H.265 Code…

一个 TypeScript 实现的高性能媒体库，支持 WebCodecs 和 Wasm。 A high-performance media library implemented in TypeScript, support WebCodecs and Wasm.

🤟 Super fast H.264/H.265 FLV player

Simple http server in Rust (Windows/Mac/Linux)

Jessibuca是一款开源的纯H5直播流播放器

[NeurIPS'23] Emergent Correspondence from Image Diffusion

Javascript HTTP Live Streaming realtime converter and player

This is the stress-ng upstream project git repository. stress-ng will stress test a computer system in various selectable ways. It was designed to exercise various physical subsystems of a computer…

MLX: An array framework for Apple silicon

Darknet/YOLO object detection framework

Codes for RoadBEV: road surface reconstruction in Bird's Eye View

nndeploy是一款模型端到端部署框架。以多端推理以及基于有向无环图模型部署为基础，致力为用户提供跨平台、简单易用、高性能的模型部署体验。

SQL powered operating system instrumentation, monitoring, and analytics.

The BNG Blaster is an open-source network tester for access and routing protocols.

Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.

Implementation of paper - DEYO: DETR with YOLO for End-to-End Object Detection

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

[ICCV 2023] A large-scale high-resolution dataset satisfies all important data features about document shadow, covers a large number of document shadow images.

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

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