Awesome-AI-Tech-Repository

A curated full-stack AI knowledge repository, systematically collecting official documentation, technical tutorials, open-source projects, academic papers, datasets and development tools, covering the whole technical path from basic mathematical foundation to large model engineering deployment.

📂 Catalog Navigation

• 00_Base_Math_Python | Mathematical foundation + Data science Python basics
• 01_ML_Traditional | Classical machine learning algorithms & Scikit-learn official docs
• 02_DL_DeepLearning | Deep learning theory + PyTorch/TensorFlow framework documents
• 03_NLP | Natural Language Processing & pre-trained model materials
• 04_CV_ComputerVision | Computer Vision、YOLO、OpenCV、OCR development resources
• 05_LLM_LargeModel | Open-source large model, fine-tuning, quantization & inference documents
• 06_RAG_Application | RAG framework specification & practical development cases
• 07_AI_Agent | AI Agent, tool invocation & multi-agent development
• 08_AI_Deploy_Engineer | AI service containerization, TensorRT & production deployment practice
• 09_Extra_Study | Personal technical summaries & scattered learning notes
• 10_Course_Books_Paper | Classic textbooks, open courses & top conference papers
• 11_Dataset_Tools | Public datasets, vector database & common AI development tools

📌 Repository Specification

1. Each subdirectory stores Resource_List.md uniformly, fixed format: Resource Name | Official Document Link | Extended Tutorial | Supplementary Notes
2. No model weight files & oversized raw datasets stored in repo, only retain official download address to keep repository lightweight
3. Resources sorted by Beginner → Intermediate → Advanced for progressive learning

🤝 Contribution Rules

• Submit resource demand or invalid link feedback via Issues;
• Supplement high-quality resources by PR, check CONTRIBUTING.md for detailed submission standards.

📄 License

This repository follows MIT License, free for personal learning & non-commercial usage.