AI 开源项目榜。
A TensorFlow & Deep Learning online course I taught in 2016
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
Deep Reinforcement Learning: Zero to Hero!
ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理
Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
A clear, concise, simple yet powerful and efficient API for deep learning.
Feature engineering and selection open-source Python library compatible with sklearn.
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
A curated list of pretrained sentence and word embedding models
OpenAGI: When LLM Meets Domain Experts
A lightweight framework for building LLM-based agents
:pencil2: Web-based image segmentation tool for object detection, localization, and keypoints
Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+
深度有趣
📚 Personal collection of ChatGPT prompts for developers!
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
ECCV 2026 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2026论文和开源项目
AI code-writing assistant that understands data content
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
InferSent sentence embeddings
Transcription, forced alignment, and audio indexing with OpenAI's Whisper
PyMuPDF4LLM
relation-graph is an relationship graph component for React/Vue/Svelte relationship data visualization/edit. Through its slot-based customization model, users can fully customize graph elements with plain React/Vue/Svelte/HTML components, relation-graph also uses an LLM-friendly architecture and provides knowledge content.
The purpose of this project is to share knowledge on how awesome Streamlit is and can be
Reinforcement Learning in PyTorch
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation