Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

ShusenTang/Dive-into-DL-PyTorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

49Apache-2.0Jupyter Notebook

View on GitHub Website

Stars: 19,462
Forks: 5,404
Watchers: 19,462
Open issues: 78
Contributors: 8

Star history, last 90 days+23 over 6 snapshots

2026-07-24 · 19,4392026-08-06 · 19,462

Star history, last 90 days
Date	Stars
2026-07-24	19439
2026-07-25	19441
2026-07-28	19452
2026-07-30	19452
2026-07-31	19453
2026-08-06	19462

Today

+9 stars today

This week

+10 stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.05%/day

From the README


<div align=center>
<img width="500" src="img/cover.png" alt="封面"/>
</div>

[本项目](https://tangshusen.me/Dive-into-DL-PyTorch)将[《动手学深度学习》](http://zh.d2l.ai/) 原书中MXNet代码实现改为PyTorch实现。原书作者：阿斯顿·张、李沐、扎卡里 C. 立顿、亚历山大 J. 斯莫拉以及其他社区贡献者，GitHub地址：https://github.com/d2l-ai/d2l-zh

此书的[中](https://zh.d2l.ai/)[英](https://d2l.ai/)版本存在一些不同，针对此书英文版的PyTorch重构可参考[这个项目](https://github.com/dsgiitr/d2l-pytorch)。
There are some differences between the [Chinese](https://zh.d2l.ai/) and [English](https://d2l.ai/) versions of this book. For the PyTorch modifying of the English version, you can refer to [this repo](https://github.com/dsgiitr/d2l-pytorch).


## 简介
本仓库主要包含code和docs两个文件夹（外加一些数据存放在data中）。其中code文件夹就是每章相关jupyter notebook代码（基于PyTorch）；docs文件夹就是markdown格式的《动手学深度学习》书中的相关内容，然后利用[docsify](https://docsify.js.org/#/zh-cn/)将网页文档部署到GitHub Pages上，由于原书使用的是MXNet框架，所以docs内容可能与原书略有不同，但是整体内容是一样的。欢迎对本项目做出贡献或提出issue。

## 面向人群
本项目面向对深度学习感兴趣，尤其是想使用PyTorch进行深度学习的童鞋。本项目并不要求你有任何深度学习或者机器学习的背景知识，你只需了解基础的数学和编程，如基础的线性代数、微分和概率，以及基础的Python编程。

## 食用方法 
### 方法一
本仓库包含一些latex公式，但github的markdown原生是不支持公式显示的，而docs文件夹已经利用[docsify](https://docsify.js.org/#/zh-cn/)被部署到了GitHub Pages上，所以查看文档最简便的方法就是直接访问[本项目网页版](https://tangshusen.me/Dive-into-DL-PyTorch)。当然如果你还想跑一下运行相关代码的话还是得把本项目clone下来，然后运行code文件夹下相关代码。

### 方法二
你还可以在本地访问文档，先安装`docsify-cli`工具:
``` shell
npm i docsify-cli -g
```
然后将本项目clone到本地:
``` shell
git clone https://github.com/ShusenTang/Dive-into-DL-PyTorch.git
cd Dive-into-DL-PyTorch
```
然后运行一个本地服务器，这样就可以很方便的在`http://localhost:3000`实时访问文档网页渲染效果。
``` shell
docsify serve docs
```

### 方法三
如果你不想安装`docsify-cli`工具，甚至你的电脑上都没有安装`Node.js`，而出于某些原因你又想在本地浏览文档，那么你可以在`docker`容器中运行网页服务。

首先将本项目clone到本地:
``` shell
git clone https://github.com/ShusenTang/Dive-into-DL-PyTorch.git
cd Dive-into-DL-PyTorch
```
之后使用如下命令创建一个名称为「d2dl」的`docker`镜像：
``` shell
docker build -t d2dl .
```
镜像创建好后，运行如下命令创建一个新的容器：
``` shell
docker run -dp 3000:3000 d2dl
```
最后在浏览器中打开这个地址`http://localhost:3000/#/`，就能愉快地访问文档了。适合那些不想在电脑上装太多工具的小伙伴。


## 目录
* [简介]()
* [阅读指南](read_guide.md)
* [1. 深度学习简介](chapter01_DL-intro/deep-learning-intro.md)
* 2\. 预备知识
   * [2.1 环境配置](chapter02_prerequisite/2.1_install.md)
   * [2.2 数据操作](chapter02_prerequisite/2.2_tensor.md)
   * [2.3 自动求梯度](chapter02_prerequisite/2.3_autograd.md)
* 3\. 深度学习基础
   * [3.1 线性回归](chapter03_DL-basics/3.1_linear-regression.md)
   * [3.2 线性回归的从零开始实现](chapter03_DL-basics/3.2_linear-regression-scratch.md)
   * [3.3 线性回归的简洁实现](chapter03_DL-basics/3.3_linear-regression-pytorch.md)
   * [3.4 softmax回归](chapter03_DL-basics/3.4_softmax-regression.md)
   * [3.5 图像分类数据集（Fashion-MNIST）](chapter03_DL-basics/3.5_fashion-mnist.md)
   * [3.6 softmax回归的从零开始实现](chapter03_DL-basics/3.6_softmax-regression-scratch.md)
   * [3.7 softmax回归的简洁实现](chapter03_DL-basics/3.7_softmax-regression-pytorch.md)
   * [3.8 多层感知机](chapter03_DL-basics/3.8_mlp.md)
   * [3.9 多层感知机的从零开始实现](chapter03_DL-basics/3.9_mlp-scratch.md)
   * [3.10 多层感知机的简洁实现](chapter03_DL-basics/3.10_mlp-pytorch.md)
   * [3.11 模型选择、欠拟合和过拟合](chapter03_DL-basics/3.11_underfit-overfit.md)
   * [3.12 权重衰减](chapter03_DL-basics/3.12_weight-decay.md)
   * [3.13 丢弃法](chapter03_DL-basics/3.13_dropout.md)
   * [3.14 正向传播、反向传播和计算图](chapter03_DL-basics/3.14_backprop.md)
   * [3.15 数值稳定性和模型初始化](chapter03_DL-basics/3.15_numerical-stability-and-init.md)
   * [3.16 实战Kaggle比赛：房价预测](chapter03_DL-basics/3.16_kaggle-house-price.md)
* 4\. 深度学习计算
   * [4.1 模型构造](chapter04_DL_computation/4.1_model-construction.md)
   * [4.2 模型参数的访问、初始化和共享](chapter04_DL_computation/4.2_parameters.md)
   * [4.3 模型参数的延后初始化](chapter04_DL_computation/4.3_deferred-init.md)
   * [4.4 自定义层](chapter04_DL_computation/4.4_custom-layer.md)
   * [4.5 读取和存储](chapter04_DL_computation/4.5_read-write.md)
   * [4.6 GPU计算](chapter04_DL_computation/4.6_use-gpu.md)
* 5\. 卷积神经网络
   * [5.1 二维卷积层](chapter05_CNN/5.1_conv-layer.md)
   * [5.2 填充和步幅](chapter05_CNN/5.2_padding-and-strides.md)
   * [5.3 多输入通道和多输出通道](chapter05_CNN/5.3_channels.md)
   * [5.4 池化层](chapter05_CNN/5.4_pooling.md)

Excerpt of 8,083 characters

Read on GitHub

Top contributors8 shown

ShusenTang
WICT(http://www.wict.pku.edu.cn/) · China
231
zooltd
Youhan Wu · United States
4
FangmingZhou
Renmin University of China · China
1
fengredrum
Oblivion
1
npuichigo
Yuchao Zhang · Speechify
1
forest0
Southeast University · China
1
yongboy
1
YangEfei
杨逸飞 · Tsinghua University
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

49/10049

Maintenance: 5%; How recently the default branch was pushed to
Releases: 25%; Recency and cadence of tagged releases
Community: 24%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 98%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No tagged releases
Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 7 years ago
Last push: 5 years ago
Last release: none
Release tag: —
Releases in the last year: 0
Default branch: master
Size: 35k KB
Owner type: User
Owner location: Peking University, China
Discovered via: topic:computer-vision
First indexed: 14 days ago
Last synced: 9 days ago

ShusenTang/Dive-into-DL-PyTorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

49Apache-2.0Jupyter Notebook

View on GitHub Website

Stars: 19,462
Forks: 5,404
Watchers: 19,462
Open issues: 78
Contributors: 8

Star history, last 90 days+23 over 6 snapshots

2026-07-24 · 19,4392026-08-06 · 19,462

Star history, last 90 days
Date	Stars
2026-07-24	19439
2026-07-25	19441
2026-07-28	19452
2026-07-30	19452
2026-07-31	19453
2026-08-06	19462

Today

+9 stars today

This week

+10 stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.05%/day

From the README


<div align=center>
<img width="500" src="img/cover.png" alt="封面"/>
</div>

[本项目](https://tangshusen.me/Dive-into-DL-PyTorch)将[《动手学深度学习》](http://zh.d2l.ai/) 原书中MXNet代码实现改为PyTorch实现。原书作者：阿斯顿·张、李沐、扎卡里 C. 立顿、亚历山大 J. 斯莫拉以及其他社区贡献者，GitHub地址：https://github.com/d2l-ai/d2l-zh

此书的[中](https://zh.d2l.ai/)[英](https://d2l.ai/)版本存在一些不同，针对此书英文版的PyTorch重构可参考[这个项目](https://github.com/dsgiitr/d2l-pytorch)。
There are some differences between the [Chinese](https://zh.d2l.ai/) and [English](https://d2l.ai/) versions of this book. For the PyTorch modifying of the English version, you can refer to [this repo](https://github.com/dsgiitr/d2l-pytorch).


## 简介
本仓库主要包含code和docs两个文件夹（外加一些数据存放在data中）。其中code文件夹就是每章相关jupyter notebook代码（基于PyTorch）；docs文件夹就是markdown格式的《动手学深度学习》书中的相关内容，然后利用[docsify](https://docsify.js.org/#/zh-cn/)将网页文档部署到GitHub Pages上，由于原书使用的是MXNet框架，所以docs内容可能与原书略有不同，但是整体内容是一样的。欢迎对本项目做出贡献或提出issue。

## 面向人群
本项目面向对深度学习感兴趣，尤其是想使用PyTorch进行深度学习的童鞋。本项目并不要求你有任何深度学习或者机器学习的背景知识，你只需了解基础的数学和编程，如基础的线性代数、微分和概率，以及基础的Python编程。

## 食用方法 
### 方法一
本仓库包含一些latex公式，但github的markdown原生是不支持公式显示的，而docs文件夹已经利用[docsify](https://docsify.js.org/#/zh-cn/)被部署到了GitHub Pages上，所以查看文档最简便的方法就是直接访问[本项目网页版](https://tangshusen.me/Dive-into-DL-PyTorch)。当然如果你还想跑一下运行相关代码的话还是得把本项目clone下来，然后运行code文件夹下相关代码。

### 方法二
你还可以在本地访问文档，先安装`docsify-cli`工具:
``` shell
npm i docsify-cli -g
```
然后将本项目clone到本地:
``` shell
git clone https://github.com/ShusenTang/Dive-into-DL-PyTorch.git
cd Dive-into-DL-PyTorch
```
然后运行一个本地服务器，这样就可以很方便的在`http://localhost:3000`实时访问文档网页渲染效果。
``` shell
docsify serve docs
```

### 方法三
如果你不想安装`docsify-cli`工具，甚至你的电脑上都没有安装`Node.js`，而出于某些原因你又想在本地浏览文档，那么你可以在`docker`容器中运行网页服务。

首先将本项目clone到本地:
``` shell
git clone https://github.com/ShusenTang/Dive-into-DL-PyTorch.git
cd Dive-into-DL-PyTorch
```
之后使用如下命令创建一个名称为「d2dl」的`docker`镜像：
``` shell
docker build -t d2dl .
```
镜像创建好后，运行如下命令创建一个新的容器：
``` shell
docker run -dp 3000:3000 d2dl
```
最后在浏览器中打开这个地址`http://localhost:3000/#/`，就能愉快地访问文档了。适合那些不想在电脑上装太多工具的小伙伴。


## 目录
* [简介]()
* [阅读指南](read_guide.md)
* [1. 深度学习简介](chapter01_DL-intro/deep-learning-intro.md)
* 2\. 预备知识
   * [2.1 环境配置](chapter02_prerequisite/2.1_install.md)
   * [2.2 数据操作](chapter02_prerequisite/2.2_tensor.md)
   * [2.3 自动求梯度](chapter02_prerequisite/2.3_autograd.md)
* 3\. 深度学习基础
   * [3.1 线性回归](chapter03_DL-basics/3.1_linear-regression.md)
   * [3.2 线性回归的从零开始实现](chapter03_DL-basics/3.2_linear-regression-scratch.md)
   * [3.3 线性回归的简洁实现](chapter03_DL-basics/3.3_linear-regression-pytorch.md)
   * [3.4 softmax回归](chapter03_DL-basics/3.4_softmax-regression.md)
   * [3.5 图像分类数据集（Fashion-MNIST）](chapter03_DL-basics/3.5_fashion-mnist.md)
   * [3.6 softmax回归的从零开始实现](chapter03_DL-basics/3.6_softmax-regression-scratch.md)
   * [3.7 softmax回归的简洁实现](chapter03_DL-basics/3.7_softmax-regression-pytorch.md)
   * [3.8 多层感知机](chapter03_DL-basics/3.8_mlp.md)
   * [3.9 多层感知机的从零开始实现](chapter03_DL-basics/3.9_mlp-scratch.md)
   * [3.10 多层感知机的简洁实现](chapter03_DL-basics/3.10_mlp-pytorch.md)
   * [3.11 模型选择、欠拟合和过拟合](chapter03_DL-basics/3.11_underfit-overfit.md)
   * [3.12 权重衰减](chapter03_DL-basics/3.12_weight-decay.md)
   * [3.13 丢弃法](chapter03_DL-basics/3.13_dropout.md)
   * [3.14 正向传播、反向传播和计算图](chapter03_DL-basics/3.14_backprop.md)
   * [3.15 数值稳定性和模型初始化](chapter03_DL-basics/3.15_numerical-stability-and-init.md)
   * [3.16 实战Kaggle比赛：房价预测](chapter03_DL-basics/3.16_kaggle-house-price.md)
* 4\. 深度学习计算
   * [4.1 模型构造](chapter04_DL_computation/4.1_model-construction.md)
   * [4.2 模型参数的访问、初始化和共享](chapter04_DL_computation/4.2_parameters.md)
   * [4.3 模型参数的延后初始化](chapter04_DL_computation/4.3_deferred-init.md)
   * [4.4 自定义层](chapter04_DL_computation/4.4_custom-layer.md)
   * [4.5 读取和存储](chapter04_DL_computation/4.5_read-write.md)
   * [4.6 GPU计算](chapter04_DL_computation/4.6_use-gpu.md)
* 5\. 卷积神经网络
   * [5.1 二维卷积层](chapter05_CNN/5.1_conv-layer.md)
   * [5.2 填充和步幅](chapter05_CNN/5.2_padding-and-strides.md)
   * [5.3 多输入通道和多输出通道](chapter05_CNN/5.3_channels.md)
   * [5.4 池化层](chapter05_CNN/5.4_pooling.md)

Excerpt of 8,083 characters

Read on GitHub

Top contributors8 shown

ShusenTang
WICT(http://www.wict.pku.edu.cn/) · China
231
zooltd
Youhan Wu · United States
4
FangmingZhou
Renmin University of China · China
1
fengredrum
Oblivion
1
npuichigo
Yuchao Zhang · Speechify
1
forest0
Southeast University · China
1
yongboy
1
YangEfei
杨逸飞 · Tsinghua University
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

49/10049

Maintenance: 5%; How recently the default branch was pushed to
Releases: 25%; Recency and cadence of tagged releases
Community: 24%; Contributor breadth and bus factor
Issue backlog: 100%; Open issues measured against the size of the audience
Documentation: 98%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No tagged releases
Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 7 years ago
Last push: 5 years ago
Last release: none
Release tag: —
Releases in the last year: 0
Default branch: master
Size: 35k KB
Owner type: User
Owner location: Peking University, China
Discovered via: topic:computer-vision
First indexed: 14 days ago
Last synced: 9 days ago

Top AI Repos — open-source AI, indexed and scored

ShusenTang/Dive-into-DL-PyTorch

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

ShusenTang/Dive-into-DL-PyTorch

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details