深度学习

PyTorch

PyTorch 官方 Tutorial, Website

Pytorch官网快速入门

内容：Tensor（向量）、autograd（梯度下降）、神经元网络等基本概念。

可以点击网页左上角的下面两个链接，进行在线实验：

• “Run in Microsof”t Learn”，在微软网络开发环境中运行
  • 浏览器中运行，中文界面
• “Run in Google Colab”，在谷歌Colab网络开发环境中运行；
  • 浏览器中运行，注意需要网络支持
• “Download Notebook”，下降Jupyter Notebook在本地实验环境中运行；需要本机安装相关软件

Tutorials on Learn with Torch Lightning, Tutorial

Soumith Chintala，Deep Learning with PyTorch: A 60 Minute Blitz， 中文翻译

Berkeley CS285 Lec 3: PyTorch Tutorial, Slides, Youtube Video，Colab

斯坦福 CS 224R DRL PyTorch 入门，Colab

Huggingface

Huggingface’s tutorial, Transformers library, Diffusers library tutorial

模型调优

Google, Deep Learning Tuning Playbook, maximizing the performance of deep learning models, Github,

环境配置

Tensorflow setup on Mac M1, Webpage

课本

• Dive into Deep Learning, Interactive deep learning book with code, math, and discussions, Website

工具

• PyTorch Lightning - a lightweight PyTorch wrapper for high-performance AI research. Think of it as a framework for organizing your PyTorch code.
• Hydra - a framework for elegantly configuring complex applications. The key feature is the ability to dynamically create a hierarchical configuration by composition and override it through config files and the command line.
• PyTorch Lightning + Hydra Github Project Template. A very user-friendly template for ML experimentation. Github, 3.3k stars