AI 开源项目榜。
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
Internet-scale Neural Networks
Generate music based on natural language prompts using LLMs running locally
一款全面的、便捷的cocos creator AI MCP服务插件,适用于3.8.0以上cocos版本,一键安装,一键启动。A comprehensive and convenient cocos creator AI MCP service plug-in, suitable for cocos versions above 3.8.0, one-click installation and one-click start.
SUSI AI for Google Assistant
A paper list of some recent Transformer-based CV works.
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
前端后端同时开源。 Ai-to-pptx是一个使用AI技术(DeepSeek)制作PPTX的助手,支持在线生成和导出PPTX。 主要功能: 1 使用DeepSeek等大语言模型来生成大纲 2 生成PPTX的时候可以选择不同的模板 3 支持导出PPTX
Algorithmic trading with deep learning experiments
中文命名实体识别,实体抽取,tensorflow,pytorch,BiLSTM+CRF
ModelFox makes it easy to train, deploy, and monitor machine learning models.
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
The collaboration workspace for Machine Learning
Automated CAPTCHA solver usage examples.
Generate text images for training deep learning ocr model
[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
pix2pix demo that learns from facial landmarks and translates this into a face
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
Deep Learning Toolkit for Medical Image Analysis
AgentNetworkProtocol(ANP) is an open source protocol for agent communication. Our vision is to define how agents connect with each other, building an open, secure, and efficient collaboration network for billions of intelligent agents.
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
AppPlatform 是一个前沿的大模型应用工程,旨在通过集成的声明式编程和低代码配置工具,简化和优化大模型的训练与推理应用的开发过程。本工程为软件工程师和产品经理提供一个强大的、可扩展的环境,以支持从概念到部署的全流程 AI 应用开发。
Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
Exercises for the Deep Learning textbook at www.deeplearningbook.org
Platform for AI-powered software engineers
A ComfyUI workflows and models management extension to organize and manage all your workflows, models in one place. Seamlessly switch between workflows, as well as import, export workflows, reuse subworkflows, install models, browse your models in a single workspace
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
Curated Data Science resources (Free & Paid) to help aspiring and experienced data scientists learn, grow, and advance their careers.