李沐《动手学深度学习》PyTorch 实现版开源，瞬间登上 GitHub 热榜！

李沐，亚马逊 AI 主任科学家，名声在外！半年前，由李沐、Aston Zhang 等人合力打造的《动手学深度学习》正式上线，免费供大家阅读。这是一本面向中文读者的能运行、可讨论的深度学习教科书！

之前，红色石头就分享过这份资源，再次附上：

在线预览地址：

https://zh.d2l.ai/

GitHub 项目地址：

https://github.com/d2l-ai/d2l-zh

课程视频地址：

https://space.bilibili.com/209599371/channel/detail?cid=23541

我们知道，作为 MXNet 的作者之一，李沐的这本《动手学深度学习》也是使用 MXNet 框架写成的。但是很多入坑机器学习的萌新们使用的却是 PyTorch。如果有教材对应的 PyTorch 实现代码就更好了！

撒花！今天就给大家带来这本书的 PyTorch 实现源码。最近，来自印度理工学院的数据科学小组，把《动手学深度学习》从 MXNet “翻译”成了 PyTorch，经过 3 个月的努力，这个项目已经基本完成，并登上了 GitHub 热榜。

首先放上这份资源的 GitHub 地址：

https://github.com/dsgiitr/d2l-pytorch

详细目录如下：

• Ch02 Installation
  • Installation
• Ch03 Introduction
  • Introduction
• Ch04 The Preliminaries: A Crashcourse
  • 4.1 Data Manipulation
  • 4.2 Linear Algebra
  • 4.3 Automatic Differentiation
  • 4.4 Probability and Statistics
  • 4.5 Naive Bayes Classification
  • 4.6 Documentation
• Ch05 Linear Neural Networks
  • 5.1 Linear Regression
  • 5.2 Linear Regression Implementation from Scratch
  • 5.3 Concise Implementation of Linear Regression
  • 5.4 Softmax Regression
  • 5.5 Image Classification Data (Fashion-MNIST)
  • 5.6 Implementation of Softmax Regression from Scratch
  • 5.7 Concise Implementation of Softmax Regression
• Ch06 Multilayer Perceptrons
  • 6.1 Multilayer Perceptron
  • 6.2 Implementation of Multilayer Perceptron from Scratch
  • 6.3 Concise Implementation of Multilayer Perceptron
  • 6.4 Model Selection Underfitting and Overfitting
  • 6.5 Weight Decay
  • 6.6 Dropout
  • 6.7 Forward Propagation Backward Propagation and Computational Graphs
  • 6.8 Numerical Stability and Initialization
  • 6.9 Considering the Environment
  • 6.10 Predicting House Prices on Kaggle
• Ch07 Deep Learning Computation
  • 7.1 Layers and Blocks
  • 7.2 Parameter Management
  • 7.3 Deferred Initialization
  • 7.4 Custom Layers
  • 7.5 File I/O
  • 7.6 GPUs
• Ch08 Convolutional Neural Networks
  • 8.1 From Dense Layers to Convolutions
  • 8.2 Convolutions for Images
  • 8.3 Padding and Stride
  • 8.4 Multiple Input and Output Channels
  • 8.5 Pooling
  • 8.6 Convolutional Neural Networks (LeNet)
• Ch09 Modern Convolutional Networks
  • 9.1 Deep Convolutional Neural Networks (AlexNet)
  • 9.2 Networks Using Blocks (VGG)
  • 9.3 Network in Network (NiN)
  • 9.4 Networks with Parallel Concatenations (GoogLeNet)
  • 9.5 Batch Normalization
  • 9.6 Residual Networks (ResNet)
  • 9.7 Densely Connected Networks (DenseNet)
• Ch10 Recurrent Neural Networks
  • 10.1 Sequence Models
  • 10.2 Language Models
  • 10.3 Recurrent Neural Networks
  • 10.4 Text Preprocessing
  • 10.5 Implementation of Recurrent Neural Networks from Scratch
  • 10.6 Concise Implementation of Recurrent Neural Networks
  • 10.7 Backpropagation Through Time
  • 10.8 Gated Recurrent Units (GRU)
  • 10.9 Long Short Term Memory (LSTM)
  • 10.10 Deep Recurrent Neural Networks
  • 10.11 Bidirectional Recurrent Neural Networks
  • 10.12 Machine Translation and DataSets
  • 10.13 Encoder-Decoder Architecture
  • 10.14 Sequence to Sequence
  • 10.15 Beam Search
• Ch11 Attention Mechanism
  • 11.1 Attention Mechanism
  • 11.2 Sequence to Sequence with Attention Mechanism
  • 11.3 Transformer
• Ch12 Optimization Algorithms
  • 12.1 Optimization and Deep Learning
  • 12.2 Convexity
  • 12.3 Gradient Descent
  • 12.4 Stochastic Gradient Descent
  • 12.5 Mini-batch Stochastic Gradient Descent
  • 12.6 Momentum
  • 12.7 Adagrad
  • 12.8 RMSProp
  • 12.9 Adadelta
  • 12.10 Adam

其中，每一小节都是可以运行的 Jupyter 记事本，你可以自由修改代码和超参数来获取及时反馈，从而积累深度学习的实战经验。

目前，PyTorch 代码还有 6 个小节没有完成，但整体的完成度已经很高了！开发团队希望更多的爱好者加入进来，贡献一份力量！

最后，再次附上 GitHub 地址：

https://github.com/dsgiitr/d2l-pytorch