Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

本项目是一个手势识别系统，支持单双手静态和动态手势的数据收集、模型训练以及可视化展示。通过使用Mediapipe库进行手部关键点检测，结合多种机器学习和深度学习模型进行手势分类，同时提供了数据增强功能以提高模型的泛化能力。

A repo for llm on ncnn

Fully Open Framework for Democratized Multimodal Training

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

This is a resouce list for low light image enhancement

[CVPR 2022] This is the official code for the paper "Toward Fast, Flexible, and Robust Low-Light Image Enhancement".

Single file minimal Vulkan example(s)

[CVPR 2024] Real-Time HDR Video Reconstruction

Denoise,HDR,Isppipeline,Image-processing(图形处理),camera, Isp ,HDRplus

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

openwrt自动化云编译（每日4时自动编译上传）

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

A fundamental toolkit designed for music, song, and audio generation

自动化编译IPQ系列固件

High Performance Chinese License Plate Recognition Framework.

多类别多目标跟踪YoloV5+sort/deepsort/bytetrack/BotSort/motdt

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

一元机场官网/官方地址

A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

codes about parallel houghlines detection

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

Converts a depth map image to a normal map image using Python