Stars
Open-source game engine with a C++17 / Vulkan runtime and a Python production layer.
Pytorch implementation of FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image
使用ONNXRuntime部署百度飞桨开源PP-Vehicle车辆分析，包含车辆检测，识别车型和车辆颜色，车牌检测，车牌识别5个功能，不依赖PaddlePaddle就能运行，包含C++和Python两个版本的程序
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
A enterprise-grade Voice Activity Detector from modelscope and funasr.
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断
This package, developed as part of our research detailed in the Chroma Technical Report, provides tools for text chunking and evaluation. It allows users to compare different chunking methods and i…
A BLE service on raspberry pi for wifi configuration and wireless control.
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
AI powered speech denoising and enhancement
libLoL (LoongArch on LoongArch): Old-world ABI compatibility runtime
“Debian 小药盒”，一个用来包装 Debian 安装介质的盒子设计和介绍用的说明书。
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
code for learning trajectory dependencies for human motion prediction
这里是改进了pytorch的DataParallel, 用来平衡第一个GPU的显存使用量
Approaching (Almost) Any Machine Learning Problem中译版，在线文档地址：https://ytzfhqs.github.io/AAAMLP-CN/
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
✯ 可直连访问的电视/广播图标库与相关工具项目 ✯ 🔕 永久免费 直连访问 完整开源 不断完善的台标 支持IPv4/IPv6双栈访问 🔕
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
将Typora伪装成LaTeX的中文样式主题，本科生轻量级课程论文撰写的好帮手。This is a theme disguising Typora into Chinese LaTeX style.