A free, code-first online course and notebook collection teaching deep learning with PyTorch, from fundamentals through model deployment.
TingsongYu/PyTorch_Tutorial
Companion code for the Chinese book 《PyTorch实用教程》, covering PyTorch model training workflows with runnable Python examples.
- Stars
- 8,029
- Forks
- 1,738
- Open issues
- 34
- Last commit
- 5 days ago
What is it?
This repository holds the example code that accompanies the Chinese-language book 《PyTorch实用教程》 (Practical PyTorch Tutorial). It is aimed at readers who want to learn how to train deep learning models with PyTorch, and the code follows the book's chapters step by step.
The repository's setup instructions cover installing dependencies from requirements.txt and then installing PyTorch and torchvision separately, using the CPU build. The code was tested on Windows 10 with Python 3.5 and PyTorch 0.4.0, and on macOS with Python 3.6 and PyTorch 0.4.1 or 1.0.0, so the examples target older PyTorch versions.
A second edition of the book is published online and adds deep learning application cases in computer vision, NLP and LLMs, along with ONNX and TensorRT inference deployment tutorials.
Key features
- 01Companion code for a Chinese PyTorch model training tutorial book
- 02Organized by book chapters for step-by-step learning
- 03Dependencies listed in requirements.txt for easy setup
- 04Examples tested on Windows 10 and macOS with older PyTorch versions
Use cases
- Learning PyTorch model training as a Chinese-speaking beginner
- Following along with the book's examples chapter by chapter
- Finding a reference for basic PyTorch training code
Quick start
- 1
Install the Python dependencies from requirements.txt
pip install -r requirements.txt - 2
Manually install PyTorch and torchvision (CPU build) from the official site
Things to know
- The README tests only old versions (Python 3.5/3.6, PyTorch 0.4 to 1.0), so newer environments may need adjustments.
- The README gives no open-source license, so reuse terms are unclear.
- The companion code is for a Chinese book, with docs and comments mainly in Chinese.
Topics
FAQ
- What is PyTorch_Tutorial?
- Companion code for the Chinese book 《PyTorch实用教程》, covering PyTorch model training workflows with runnable Python examples. This repository holds the example code that accompanies the Chinese-language book 《PyTorch实用教程》 (Practical PyTorch Tutorial). It is aimed at readers who want to learn how to train deep learning models with PyTorch, and the code follows the book's chapters step by step.
- Is PyTorch_Tutorial free to use? What license does it have?
- PyTorch_Tutorial has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is PyTorch_Tutorial still maintained?
- Actively maintained. The last commit to PyTorch_Tutorial was on Nov 1, 2026.
- What can I use PyTorch_Tutorial for?
- Learning PyTorch model training as a Chinese-speaking beginner Following along with the book's examples chapter by chapter Finding a reference for basic PyTorch training code
- How do I install PyTorch_Tutorial?
- Install the Python dependencies from requirements.txt: pip install -r requirements.txt Manually install PyTorch and torchvision (CPU build) from the official site
- Where can I get PyTorch_Tutorial?
- The source code and installation instructions are on GitHub: https://github.com/TingsongYu/PyTorch_Tutorial
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A visual, timeline-based learning roadmap that traces deep learning and LLM architecture families from the 1986 RNN to 2025 reasoning models.
A free, MIT-licensed course of 542 lessons that builds AI engineering concepts from scratch in Python, TypeScript, Rust and Julia.
An educational resource from OpenAI for learning deep reinforcement learning, with intros, key papers, exercises and short algorithm implementations.
A hands-on, beginner-oriented tutorial for training and deploying image classification neural networks with Caffe and NVIDIA DIGITS, no prior AI background needed.
A Chinese-language course-style repository covering AI math basics, machine learning, deep learning, Transformer, BERT and competition case studies, with annotated code and datasets.