Skip to content
项目分类

机器学习 · GitHub

发现模型训练、评估与推理框架,比较深度学习和机器学习项目的社区关注度。

实用 GitHub 项目

4,743 个项目

kedro

kedro-org

11,053星标+224小时
kedro preview

Kedro 是一个面向生产环境的数据科学工具集。它采用软件工程最佳实践,帮助你构建可复现、易维护且模块化的数据工程和数据科学工作流。

  • Project Template - A standard, modifiable and easy-to-use project template based on Cookiecutter Data Science.
  • Data Catalog - A series of lightweight data connectors used to save and load data across many different file formats and file systems, including local and network file systems, cloud object stores, and HDFS. The Data Catalog also includes data and model versioning for file-based systems.

Muon

KellerJordan

2,938星标+224小时

Muon 是一种用于神经网络隐藏层的优化器。

manga-ocr

kha-white

2,837星标+224小时
manga-ocr preview

用于识别日文文本的光学字符识别工具,主要面向日本漫画。

机器学习PythonApache-2.0GitHub

yomitoku

kotaro-kinoshita

1,702星标+224小时
yomitoku preview

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

LettuceDetect

KRLabsOrg

624星标+224小时
LettuceDetect preview

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

  • Returns exact character spans instead of only an answer-level clean/flagged verdict.
  • Supports RAG prose, multilingual QA, code-agent answers, and developer-tool output.
989星标+224小时
vectordb-recipes preview

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

机器学习Jupyter NotebookApache-2.0GitHub

lc0

LeelaChessZero

3,280星标+224小时
lc0 preview

Open source neural network chess engine with GPU acceleration and broad hardware support.

lightly-train

lightly-ai

1,734星标+224小时
lightly-train preview

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

  • Python, Command Line, and Docker support
  • Built for high performance including multi-GPU and multi-node support
机器学习PythonAGPL-3.0GitHub

LimiX

limix-ldm-ai

4,414星标+224小时
LimiX preview

LimiX:释放面向通用智能的结构化数据建模能力 https://arxiv.org/abs/2609.17488

deepxde

lululxvi

4,506星标+224小时
deepxde preview

A library for scientific machine learning and physics-informed learning

  • enables the user code to be compact, resembling closely the mathematical formulation.
  • 5 types of boundary conditions (BCs): Dirichlet, Neumann, Robin, periodic, and a general BC, which can be defined on an arbitrary domain or on a point set; and approximate distance functions for hard constraints.
机器学习PythonLGPL-2.1GitHub

RT-DETR

lyuwenyu

5,665星标+224小时
RT-DETR preview

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

机器学习PythonApache-2.0GitHub

CLAM

mahmoodlab

1,773星标+224小时
CLAM preview

Open source tools for computational pathology - Nature BME

机器学习PythonGPL-3.0GitHub

gust

marciok

393星标+224小时
gust preview

A Task-Based Workflow Orchestration Engine

  • Task orchestration with Cron-style scheduling and dependency-aware DAGs via the Gust DSL.
  • YAML and Shell DAG support for orchestrating shell commands and scripts.
2,259星标+224小时
MATLAB-Simulink-Challenge-Project-Hub preview

This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.

SwarmUI

mcmonkeyprojects

4,776星标+224小时
SwarmUI preview

SwarmUI(前身为 StableSwarmUI),一款模块化的 Stable Diffusion 网页界面,注重让强大工具易于使用,并兼顾高性能和可扩展性。

YOLOX

Megvii-BaseDetection

10,704星标+224小时
YOLOX preview

YOLOX 是一款高性能、无锚框的 YOLO,性能超越 YOLOv3~v5,并支持 MegEngine、ONNX、TensorRT、ncnn 和 OpenVINO。文档:https://yolox.readthedocs.io/

机器学习PythonApache-2.0GitHub

llama-cookbook

meta-llama

18,590星标+224小时

欢迎来到 Llama Cookbook!这是使用 Llama 构建应用的指南,涵盖推理、微调和 RAG 的入门方法。我们还将介绍如何使用 Llama 模型系列解决端到端问题,以及如何在各种提供商服务中使用这些模型。

机器学习Jupyter NotebookMITGitHub

mindspore

mindspore-ai

4,726星标+224小时
mindspore preview

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

机器学习C++Apache-2.0GitHub

laya-mlx

mizorewww

7,093星标+224小时
laya-mlx preview

适用于 Laya 类型化决策模型的原生 MLX 运行时——在 M3 Max 上实现 7–14 毫秒的短决策。不支持文本生成、PyTorch 或云 API。

机器学习PythonApache-2.0GitHub