整理 & 网页支持

tngt · Dec 2, 2019 · 09c2ebc · 09c2ebc
1 parent 5f58f50
commit 09c2ebc
Show file tree

Hide file tree

Showing 181 changed files with 5,276 additions and 37 deletions.
diff --git a/Documents (for reading)/img/cover.png b/Documents (for reading)/img/cover.png
diff --git a/...DL_Introduction/deep-learning-intro.ipynb → ...pter01_DL-intro/deep-learning-intro.ipynb b/...DL_Introduction/deep-learning-intro.ipynb → ...pter01_DL-intro/deep-learning-intro.ipynb
diff --git a/...ch2_prerequsite/2.2 data manipulate.ipynb → code/chapter02_prerequsite/2.2_tensor.ipynb b/...ch2_prerequsite/2.2 data manipulate.ipynb → code/chapter02_prerequsite/2.2_tensor.ipynb
diff --git a/...g)/ch2_prerequsite/2.3 autoGradient.ipynb → .../chapter02_prerequsite/2.3_autograd.ipynb b/...g)/ch2_prerequsite/2.3 autoGradient.ipynb → .../chapter02_prerequsite/2.3_autograd.ipynb
diff --git a/...uting)/ch2_prerequsite/2.4 document.ipynb → .../chapter02_prerequsite/2.4_document.ipynb b/...uting)/ch2_prerequsite/2.4 document.ipynb → .../chapter02_prerequsite/2.4_document.ipynb
diff --git a/...)/ch3_DL_basics/3.10_mlp-tensorflow.ipynb → ...03_DL-basics/3.10_mlp-tensorflow2.0.ipynb b/...)/ch3_DL_basics/3.10_mlp-tensorflow.ipynb → ...03_DL-basics/3.10_mlp-tensorflow2.0.ipynb
diff --git a/...ch3_DL_basics/3.11_underfit-overfit.ipynb → ...r03_DL-basics/3.11_underfit-overfit.ipynb b/...ch3_DL_basics/3.11_underfit-overfit.ipynb → ...r03_DL-basics/3.11_underfit-overfit.ipynb
diff --git a/...ecuting)/ch3_DL_basics/3.13_dropout.ipynb → code/chapter03_DL-basics/3.13_dropout.ipynb b/...ecuting)/ch3_DL_basics/3.13_dropout.ipynb → code/chapter03_DL-basics/3.13_dropout.ipynb
diff --git a/...ch3_DL_basics/3.1 linear regression.ipynb → ...r03_DL-basics/3.1_linear-regression.ipynb b/...ch3_DL_basics/3.1 linear regression.ipynb → ...r03_DL-basics/3.1_linear-regression.ipynb
diff --git a/.../3.2 linear regression from scratch.ipynb → ...asics/3.2_linear-regression-scratch.ipynb b/.../3.2 linear regression from scratch.ipynb → ...asics/3.2_linear-regression-scratch.ipynb
diff --git a/...3.3_linear-regression-tensorflow2.0.ipynb → ...3.3_linear-regression-tensorflow2.0.ipynb b/...3.3_linear-regression-tensorflow2.0.ipynb → ...3.3_linear-regression-tensorflow2.0.ipynb
diff --git a/...ng)/ch3_DL_basics/3.5_fashion-mnist.ipynb → ...apter03_DL-basics/3.5_fashion-mnist.ipynb b/...ng)/ch3_DL_basics/3.5_fashion-mnist.ipynb → ...apter03_DL-basics/3.5_fashion-mnist.ipynb
diff --git a/....7_softmax-regression-tensorflow2.0.ipynb → ....7_softmax-regression-tensorflow2.0.ipynb b/....7_softmax-regression-tensorflow2.0.ipynb → ....7_softmax-regression-tensorflow2.0.ipynb
diff --git a/...ting)/ch3_DL_basics/3.9_mlp-scratch.ipynb → ...chapter03_DL-basics/3.9_mlp-scratch.ipynb b/...ting)/ch3_DL_basics/3.9_mlp-scratch.ipynb → ...chapter03_DL-basics/3.9_mlp-scratch.ipynb
diff --git a/.../ch4_DL_computation/4.1 build model.ipynb → ...-computation/4.1_model-construction.ipynb b/.../ch4_DL_computation/4.1 build model.ipynb → ...-computation/4.1_model-construction.ipynb
diff --git a/... access, initialization and sharing.ipynb → ...ter04_DL-computation/4.2_parameters.ipynb b/... access, initialization and sharing.ipynb → ...ter04_DL-computation/4.2_parameters.ipynb
diff --git a/...ch4_DL_computation/4.4 custom layer.ipynb → ...r04_DL-computation/4.4_custom-layer.ipynb b/...ch4_DL_computation/4.4 custom layer.ipynb → ...r04_DL-computation/4.4_custom-layer.ipynb
diff --git a/...)/ch4_DL_computation/4.5 read-write.ipynb → ...ter04_DL-computation/4.5_read-write.ipynb b/...)/ch4_DL_computation/4.5 read-write.ipynb → ...ter04_DL-computation/4.5_read-write.ipynb
diff --git a/...ing)/ch4_DL_computation/4.5saved_model.h5 → ...hapter04_DL-computation/4.5saved_model.h5 b/...ing)/ch4_DL_computation/4.5saved_model.h5 → ...hapter04_DL-computation/4.5saved_model.h5
diff --git a/...ing)/ch4_DL_computation/4.6 use-GPU.ipynb → ...hapter04_DL-computation/4.6_use-GPU.ipynb b/...ing)/ch4_DL_computation/4.6 use-GPU.ipynb → ...hapter04_DL-computation/4.6_use-GPU.ipynb
diff --git a/.../5.1 2-dimentional convolutional NN.ipynb → code/chapter05_CNN/5.1_conv-layer.ipynb b/.../5.1 2-dimentional convolutional NN.ipynb → code/chapter05_CNN/5.1_conv-layer.ipynb
diff --git a/...nvolution_NN/5.2 padding and stride.ipynb → ...apter05_CNN/5.2_padding-and-strides.ipynb b/...nvolution_NN/5.2 padding and stride.ipynb → ...apter05_CNN/5.2_padding-and-strides.ipynb
diff --git a/...5_convolution_NN/5.3 multi-channels.ipynb → code/chapter05_CNN/5.3_channels.ipynb b/...5_convolution_NN/5.3 multi-channels.ipynb → code/chapter05_CNN/5.3_channels.ipynb
diff --git a/...h5_convolution_NN/5.4 pooling layer.ipynb → code/chapter05_CNN/5.4_pooling.ipynb b/...h5_convolution_NN/5.4 pooling layer.ipynb → code/chapter05_CNN/5.4_pooling.ipynb
diff --git a/...tion_NN/5.5 Convolution net (LeNet).ipynb → code/chapter05_CNN/5.5_lenet.ipynb b/...tion_NN/5.5 Convolution net (LeNet).ipynb → code/chapter05_CNN/5.5_lenet.ipynb
diff --git a/Codes (for executing)/ch6_RNN/6.2_rnn.ipynb → code/chapter06_RNN/6.2_rnn.ipynb b/Codes (for executing)/ch6_RNN/6.2_rnn.ipynb → code/chapter06_RNN/6.2_rnn.ipynb
diff --git a/docs/.nojekyll b/docs/.nojekyll
diff --git a/README.md → docs/README.md b/README.md → docs/README.md
@@ -1,12 +1,13 @@
 <div align=center>
-<img width="500" src="imags/cover1.PNG" alt="封面"/>
+<img width="500" src="img/cover.png" alt="封面"/>
 </div>
 
 [本项目](TODO)将[《动手学深度学习》](http://zh.d2l.ai/) 原书中MXNet代码实现改为TensorFlow2.0实现。经过我的导师咨询李沐老师，这个项目的实施已得到李沐老师的同意。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，本项目主要针对此书的中文版进行TensorFlow2.0重构。另外，针对此书中文版的Pytorch重构可以参考[这个项目](https://github.com/ShusenTang/Dive-into-DL-PyTorch)
+此书的[中](https://zh.d2l.ai/)、[英](https://d2l.ai/)版本存在一些不同，本项目主要针对此书的中文版进行TensorFlow2.0重构。另外，针对此书中文版的Pytorch重构可以参考[这个项目](https://github.com/ShusenTang/Dive-into-DL-PyTorch)。
+
+**现已更新到第五章，持续更新中。。。**
 
-## 现已更新到第五章，持续更新中。。。
 ## 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TensorFlow）；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。
 
@@ -15,7 +16,7 @@
 
 ## 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](TODO)尚未实现。。。。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。
+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](TODO)。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:
@@ -34,44 +35,44 @@ docsify serve docs
 
 
 ## 目录
-* [简介](README.md)
+* [简介]()
 * [阅读指南](read_guide.md)
-* [1. 深度学习简介](https://github.com/TrickyGo/tensorflow-2.0-dive-into-dl/blob/master/Documents%20(for%20reading)/ch1_DL_Introduction/deep-learning-intro.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch2_prerequsite/2.1_install.md)
-   * [2.2 数据操作](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch2_prerequsite/2.2%20data%20manipulate.md)
-   * [2.3 自动求梯度](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch2_prerequsite/2.3%20autoGradient.md)
-   * [2.4 查阅文档](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch2_prerequsite/2.4%20document.md)
+   * [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)
+   * [2.4 查阅文档](chapter02_prerequisite/2.4_document.md)
 * 3\. 深度学习基础
-   * [3.1 线性回归](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.1_linear-regression.md)
-   * [3.2 线性回归的从零开始实现](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.2_linear-regression-scratch.md)
-   * [3.3 线性回归的简洁实现](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.3_linear-regression-tensorflow2.0%20.md)
-   * [3.4 softmax回归](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.4_softmax-regression.md)
-   * [3.5 图像分类数据集（Fashion-MNIST）](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.5_fashion-mnist.md)
+   * [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-tensorflow2.0.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.7_softmax-regression-tensorflow2.0.md)
+   * [3.7 softmax回归的简洁实现](chapter03_DL-basics/3.7_softmax-regression-tensorflow2.0.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch3_DL_basics/3.9_mlp-scratch.ipynb)
-   * [3.10 多层感知机的简洁实现](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch3_DL_basics/3.10_mlp-tensorflow.ipynb)
-   * [3.11 模型选择、欠拟合和过拟合](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch3_DL_basics/3.11_underfit-overfit.ipynb)
+   * [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-tensorflow2.0.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.14_backprop.md)
-   * [3.15 数值稳定性和模型初始化](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch3_DL_basics/3.15_numerical-stability-and-init.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch4_DL_computation/4.1%20build%20model.md)
-   * [4.2 模型参数的访问、初始化和共享](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch4_DL_computation/4.2%20parameters'%20access%2C%20initialization%20and%20sharing.md)
+   * [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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch4_DL_computation/4.4%20custom%20layer.md)
-   * [4.5 读取和存储](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch4_DL_computation/4.5%20read-write.md)
-   * [4.6 GPU计算](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch4_DL_computation/4.6%20use-GPU.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](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/tree/master/Codes%20(for%20executing)/ch5_convolution_NN)
-   * [5.2 填充和步幅](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch5_convolution_NN/5.2%20padding%20and%20stride.ipynb)
-   * [5.3 多输入通道和多输出通道](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch5_convolution_NN/5.3%20multi-channels.ipynb)
-   * [5.4 池化层](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch5_convolution_NN/5.4%20pooling%20layer.ipynb)
-   * [5.5 卷积神经网络（LeNet）](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Codes%20(for%20executing)/ch5_convolution_NN/5.5%20Convolution%20net%20(LeNet).ipynb)
+   * [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)
+   * [5.5 卷积神经网络（LeNet）](chapter05_CNN/5.5_lenet.md)
    * [5.6 深度卷积神经网络（AlexNet）](chapter05_CNN/5.6_alexnet.md)
    * [5.7 使用重复元素的网络（VGG）](chapter05_CNN/5.7_vgg.md)
    * [5.8 网络中的网络（NiN）](chapter05_CNN/5.8_nin.md)
@@ -80,7 +81,7 @@ docsify serve docs
    * [5.11 残差网络（ResNet）](chapter05_CNN/5.11_resnet.md)
    * [5.12 稠密连接网络（DenseNet）](chapter05_CNN/5.12_densenet.md)
 * 6\. 循环神经网络
-   * [6.1 语言模型](https://github.com/TrickyGo/Dive-into-DL-TensorFlow2.0/blob/master/Documents%20(for%20reading)/ch6_RNN/6.1_lang-model.md)
+   * [6.1 语言模型](chapter06_RNN/6.1_lang-model.md)
    * [6.2 循环神经网络](chapter06_RNN/6.2_rnn.md)
    * [6.3 语言模型数据集（周杰伦专辑歌词）](chapter06_RNN/6.3_lang-model-dataset.md)
    * [6.4 循环神经网络的从零开始实现](chapter06_RNN/6.4_rnn-scratch.md)
@@ -126,8 +127,6 @@ docsify serve docs
    * [10.11 注意力机制](chapter10_natural-language-processing/10.11_attention.md)
    * [10.12 机器翻译](chapter10_natural-language-processing/10.12_machine-translation.md)
 
-
-
 持续更新中......
 
 

diff --git a/docs/_sidebar.md b/docs/_sidebar.md
@@ -0,0 +1,91 @@
+* [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)
+   * [2.4 查阅文档](chapter02_prerequisite/2.4_document.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-tensorflow2.0.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-tensorflow2.0.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-tensorflow2.0.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)
+   * [5.5 卷积神经网络（LeNet）](chapter05_CNN/5.5_lenet.md)
+   * [5.6 深度卷积神经网络（AlexNet）](chapter05_CNN/5.6_alexnet.md)
+   * [5.7 使用重复元素的网络（VGG）](chapter05_CNN/5.7_vgg.md)
+   * [5.8 网络中的网络（NiN）](chapter05_CNN/5.8_nin.md)
+   * [5.9 含并行连结的网络（GoogLeNet）](chapter05_CNN/5.9_googlenet.md)
+   * [5.10 批量归一化](chapter05_CNN/5.10_batch-norm.md)
+   * [5.11 残差网络（ResNet）](chapter05_CNN/5.11_resnet.md)
+   * [5.12 稠密连接网络（DenseNet）](chapter05_CNN/5.12_densenet.md)
+* 6\. 循环神经网络
+   * [6.1 语言模型](chapter06_RNN/6.1_lang-model.md)
+   * [6.2 循环神经网络](chapter06_RNN/6.2_rnn.md)
+   * [6.3 语言模型数据集（周杰伦专辑歌词）](chapter06_RNN/6.3_lang-model-dataset.md)
+   * [6.4 循环神经网络的从零开始实现](chapter06_RNN/6.4_rnn-scratch.md)
+   * [6.5 循环神经网络的简洁实现](chapter06_RNN/6.5_rnn-pytorch.md)
+   * [6.6 通过时间反向传播](chapter06_RNN/6.6_bptt.md)
+   * [6.7 门控循环单元（GRU）](chapter06_RNN/6.7_gru.md)
+   * [6.8 长短期记忆（LSTM）](chapter06_RNN/6.8_lstm.md)
+   * [6.9 深度循环神经网络](chapter06_RNN/6.9_deep-rnn.md)
+   * [6.10 双向循环神经网络](chapter06_RNN/6.10_bi-rnn.md)
+* 7\. 优化算法
+   * [7.1 优化与深度学习](chapter07_optimization/7.1_optimization-intro.md)
+   * [7.2 梯度下降和随机梯度下降](chapter07_optimization/7.2_gd-sgd.md)
+   * [7.3 小批量随机梯度下降](chapter07_optimization/7.3_minibatch-sgd.md)
+   * [7.4 动量法](chapter07_optimization/7.4_momentum.md)
+   * [7.5 AdaGrad算法](chapter07_optimization/7.5_adagrad.md)
+   * [7.6 RMSProp算法](chapter07_optimization/7.6_rmsprop.md)
+   * [7.7 AdaDelta算法](chapter07_optimization/7.7_adadelta.md)
+   * [7.8 Adam算法](chapter07_optimization/7.8_adam.md)
+* 8\. 计算性能
+   * [8.1 命令式和符号式混合编程](chapter08_computational-performance/8.1_hybridize.md)
+   * [8.2 异步计算](chapter08_computational-performance/8.2_async-computation.md)
+   * [8.3 自动并行计算](chapter08_computational-performance/8.3_auto-parallelism.md)
+   * [8.4 多GPU计算](chapter08_computational-performance/8.4_multiple-gpus.md)
+* 9\. 计算机视觉
+   * [9.1 图像增广](chapter09_computer-vision/9.1_image-augmentation.md)
+   * [9.2 微调](chapter09_computer-vision/9.2_fine-tuning.md)
+   * [9.3 目标检测和边界框](chapter09_computer-vision/9.3_bounding-box.md)
+   * [9.4 锚框](chapter09_computer-vision/9.4_anchor.md)
+   * [9.5 多尺度目标检测](chapter09_computer-vision/9.5_multiscale-object-detection.md)
+   * [9.6 目标检测数据集（皮卡丘）](chapter09_computer-vision/9.6_object-detection-dataset.md)
+   * 待更新...
+* 10\. 自然语言处理
+   * [10.1 词嵌入（word2vec）](chapter10_natural-language-processing/10.1_word2vec.md)
+   * [10.2 近似训练](chapter10_natural-language-processing/10.2_approx-training.md)
+   * [10.3 word2vec的实现](chapter10_natural-language-processing/10.3_word2vec-pytorch.md)
+   * [10.4 子词嵌入（fastText）](chapter10_natural-language-processing/10.4_fasttext.md)
+   * [10.5 全局向量的词嵌入（GloVe）](chapter10_natural-language-processing/10.5_glove.md)
+   * [10.6 求近义词和类比词](chapter10_natural-language-processing/10.6_similarity-analogy.md)
+   * [10.7 文本情感分类：使用循环神经网络](chapter10_natural-language-processing/10.7_sentiment-analysis-rnn.md)
+   * [10.8 文本情感分类：使用卷积神经网络（textCNN）](chapter10_natural-language-processing/10.8_sentiment-analysis-cnn.md)
+   * [10.9 编码器—解码器（seq2seq）](chapter10_natural-language-processing/10.9_seq2seq.md)
+   * [10.10 束搜索](chapter10_natural-language-processing/10.10_beam-search.md)
+   * [10.11 注意力机制](chapter10_natural-language-processing/10.11_attention.md)
+   * [10.12 机器翻译](chapter10_natural-language-processing/10.12_machine-translation.md)
diff --git a/...h1_DL_Introduction/deep-learning-intro.md → ...chapter01_DL-intro/deep-learning-intro.md b/...h1_DL_Introduction/deep-learning-intro.md → ...chapter01_DL-intro/deep-learning-intro.md
diff --git a/...r reading)/ch2_prerequsite/2.1_install.md → docs/chapter02_prerequisite/2.1_install.md b/...r reading)/ch2_prerequsite/2.1_install.md → docs/chapter02_prerequisite/2.1_install.md
diff --git a/...g)/ch2_prerequsite/2.2 data manipulate.md → docs/chapter02_prerequisite/2.2_tensor.md b/...g)/ch2_prerequsite/2.2 data manipulate.md → docs/chapter02_prerequisite/2.2_tensor.md
diff --git a/...ding)/ch2_prerequsite/2.3 autoGradient.md → docs/chapter02_prerequisite/2.3_autograd.md b/...ding)/ch2_prerequsite/2.3 autoGradient.md → docs/chapter02_prerequisite/2.3_autograd.md
diff --git a/... reading)/ch2_prerequsite/2.4 document.md → docs/chapter02_prerequisite/2.4_document.md b/... reading)/ch2_prerequsite/2.4 document.md → docs/chapter02_prerequisite/2.4_document.md
diff --git a/...ing)/ch3_DL_basics/3.10_mlp-tensorflow.md → ...ter03_DL-basics/3.10_mlp-tensorflow2.0.md b/...ing)/ch3_DL_basics/3.10_mlp-tensorflow.md → ...ter03_DL-basics/3.10_mlp-tensorflow2.0.md
diff --git a/...r reading)/ch3_DL_basics/3.14_backprop.md → docs/chapter03_DL-basics/3.14_backprop.md b/...r reading)/ch3_DL_basics/3.14_backprop.md → docs/chapter03_DL-basics/3.14_backprop.md
diff --git a/...sics/3.15_numerical-stability-and-init.md → ...sics/3.15_numerical-stability-and-init.md b/...sics/3.15_numerical-stability-and-init.md → ...sics/3.15_numerical-stability-and-init.md
diff --git a/...g)/ch3_DL_basics/3.1_linear-regression.md → ...pter03_DL-basics/3.1_linear-regression.md b/...g)/ch3_DL_basics/3.1_linear-regression.md → ...pter03_DL-basics/3.1_linear-regression.md
diff --git a/...L_basics/3.2_linear-regression-scratch.md → ...L-basics/3.2_linear-regression-scratch.md b/...L_basics/3.2_linear-regression-scratch.md → ...L-basics/3.2_linear-regression-scratch.md
diff --git a/...s/3.3_linear-regression-tensorflow2.0 .md → ...cs/3.3_linear-regression-tensorflow2.0.md b/...s/3.3_linear-regression-tensorflow2.0 .md → ...cs/3.3_linear-regression-tensorflow2.0.md
diff --git a/...)/ch3_DL_basics/3.4_softmax-regression.md → ...ter03_DL-basics/3.4_softmax-regression.md b/...)/ch3_DL_basics/3.4_softmax-regression.md → ...ter03_DL-basics/3.4_softmax-regression.md
diff --git a/...ading)/ch3_DL_basics/3.5_fashion-mnist.md → .../chapter03_DL-basics/3.5_fashion-mnist.md b/...ading)/ch3_DL_basics/3.5_fashion-mnist.md → .../chapter03_DL-basics/3.5_fashion-mnist.md
@@ -1,5 +1,5 @@
 
-# 3.5. 图像分类数据集（Fashion-MNIST）¶
+# 3.5. 图像分类数据集（Fashion-MNIST）
 在介绍softmax回归的实现前我们先引入一个多类图像分类数据集。它将在后面的章节中被多次使用，以方便我们观察比较算法之间在模型精度和计算效率上的区别。图像分类数据集中最常用的是手写数字识别数据集MNIST [1]。但大部分模型在MNIST上的分类精度都超过了95%。为了更直观地观察算法之间的差异，我们将使用一个图像内容更加复杂的数据集Fashion-MNIST [2]。
 
 ## 3.5.1. 获取数据集
@@ -141,7 +141,7 @@ print('%.2f sec' % (time.time() - start))
     0.22 sec
 
 
-3.5.3. 小结
+## 3.5.3. 小结
 
 * Fashion-MNIST是一个10类服饰分类数据集，之后章节里将使用它来检验不同算法的表现。
 * 我们将高和宽分别为 h 和 w 像素的图像的形状记为 h×w 或（h，w）。

diff --git a/...s/3.7_softmax-regression-tensorflow2.0.md → ...s/3.7_softmax-regression-tensorflow2.0.md b/...s/3.7_softmax-regression-tensorflow2.0.md → ...s/3.7_softmax-regression-tensorflow2.0.md
diff --git a/...reading)/ch3_DL_basics/3.9_mlp-scratch.md → docs/chapter03_DL-basics/3.9_mlp-scratch.md b/...reading)/ch3_DL_basics/3.9_mlp-scratch.md → docs/chapter03_DL-basics/3.9_mlp-scratch.md
diff --git a/...ng)/ch4_DL_computation/4.1 build model.md → ..._DL-computation/4.1_model-construction.md b/...ng)/ch4_DL_computation/4.1 build model.md → ..._DL-computation/4.1_model-construction.md
diff --git a/...rs' access, initialization and sharing.md → ...hapter04_DL-computation/4.2_parameters.md b/...rs' access, initialization and sharing.md → ...hapter04_DL-computation/4.2_parameters.md
diff --git a/...g)/ch4_DL_computation/4.4 custom layer.md → ...pter04_DL-computation/4.4_custom-layer.md b/...g)/ch4_DL_computation/4.4 custom layer.md → ...pter04_DL-computation/4.4_custom-layer.md
diff --git a/...ing)/ch4_DL_computation/4.5 read-write.md → ...hapter04_DL-computation/4.5_read-write.md b/...ing)/ch4_DL_computation/4.5 read-write.md → ...hapter04_DL-computation/4.5_read-write.md
diff --git a/...eading)/ch4_DL_computation/4.6 use-GPU.md → docs/chapter04_DL-computation/4.6_use-GPU.md b/...eading)/ch4_DL_computation/4.6 use-GPU.md → docs/chapter04_DL-computation/4.6_use-GPU.md
diff --git a/...s (for reading)/ch6_RNN/6.1_lang-model.md → docs/chapter06_RNN/6.1_lang-model.md b/...s (for reading)/ch6_RNN/6.1_lang-model.md → docs/chapter06_RNN/6.1_lang-model.md