PyTorch-Tutorial-2nd
《Pytorch实用教程》(第二版)无论是零基础入门,还是CV、NLP、LLM项目应用,或是进阶工程化部署落地,在这里都有。相信在本书的帮助下,读者将能够轻松掌握 PyTorch 的使
What is PyTorch-Tutorial-2nd?
《Pytorch实用教程》(第二版)无论是零基础入门,还是CV、NLP、LLM项目应用,或是进阶工程化部署落地,在这里都有。相信在本书的帮助下,读者将能够轻松掌握 PyTorch 的使用,成为一名优秀的深度学习工程师。
Overview of PyTorch-Tutorial-2nd
What it is
PyTorch-Tutorial-2nd is the second edition of the PyTorch Practical Tutorial, an open-source educational resource that covers the full workflow of a deep learning engineer. It is divided into three parts: an introductory section on PyTorch basics, an application section covering computer vision, natural language processing, and large language models, and a deployment section focusing on ONNX and TensorRT for model inference and quantization.
Key features
- Structured into three parts: basics, applications, and deployment
- Covers eight computer vision tasks including image classification, segmentation, object detection, tracking, GAN generation, diffusion generation, image captioning, and image retrieval
- Covers five NLP tasks: text classification, machine translation, named entity recognition, QA, and text generation
- Includes four open-source Chinese LLMs: Qwen, ChatGLM, Baichuan, and Yi
- Provides practical deployment with ONNX and TensorRT, including PTQ and QAT quantization
Use cases
This tutorial is intended for AI self-learners, AI product managers, students, and professionals transitioning into deep learning. It can be used as a structured learning path from zero to production-level deployment, or as a reference for implementing common CV, NLP, and LLM projects.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. The tutorial is open source and free to read online.
Based on the project's public README and repository metadata.