diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index f77a171c1b28663adfe52fce876168b04a04cfb5..8359afe36571b8335afe2f528dc08285e4efce48 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -26,9 +26,11 @@
     -   id: remove-tabs
         files: \.md$
 -   repo: https://github.com/reyoung/pre-commit-hooks-jinja-compile.git
-    sha: 85ad800cbc9c60a64230d60971aa9576fd57e508
+    sha: 4a369cc72a4a2b8d3813ab8cc17abb5f5b21ef6c
     hooks:
     -   id: convert-jinja2-into-html
+        # The argument means repleace filename from pattern `.*/([^/]*)\.tmpl` to `\1`
+        args: ['--filename_pattern=.*/([^/]*)\.tmpl', '--filename_repl=\1']
 -   repo: local
     hooks:
     -   id: convert-markdown-into-html
diff --git a/.pre-commit-hooks/convert_markdown_into_html.py b/.pre-commit-hooks/convert_markdown_into_html.py
index acb3d0ad0559b35a6b1f86283c1193c8935c5caa..66f44ef23c5d9a82436dfbe4b6bcdfc4e69ab55a 100644
--- a/.pre-commit-hooks/convert_markdown_into_html.py
+++ b/.pre-commit-hooks/convert_markdown_into_html.py
@@ -18,13 +18,13 @@ HEAD = """
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/index.en.html.json b/.tools/templates/index.en.html.json
similarity index 100%
rename from index.en.html.json
rename to .tools/templates/index.en.html.json
diff --git a/index.en.html.tmpl b/.tools/templates/index.en.html.tmpl
similarity index 100%
rename from index.en.html.tmpl
rename to .tools/templates/index.en.html.tmpl
diff --git a/index.html.json b/.tools/templates/index.html.json
similarity index 100%
rename from index.html.json
rename to .tools/templates/index.html.json
diff --git a/index.html.tmpl b/.tools/templates/index.html.tmpl
similarity index 98%
rename from index.html.tmpl
rename to .tools/templates/index.html.tmpl
index 3729ec62426c393c08afb934fcfc2d61832cfcd3..2762bc0a7bb15f0260d35d9571429171d972657c 100644
--- a/index.html.tmpl
+++ b/.tools/templates/index.html.tmpl
@@ -11,6 +11,7 @@
 * {
     font-family:"Roboto","Lato","proxima-nova","Helvetica Neue",Arial,sans-serif;
 }
+
 .left-panel {
     background: #E5E6EA;
 }
@@ -68,7 +69,7 @@
 <body>
     <nav class="navbar navbar-toggleable-md navbar-inverse bg-inverse">
         <a class="navbar-brand mr-auto" href="#">
-            <img alt="PaddlePaddle" src="./.theme/PP_w.png">
+            <img alt="PaddlePaddle" src="./.tools/theme/PP_w.png">
         </a>
         <ul class="nav navbar-nav">
           <li class="nav-item">
diff --git a/.theme/PP_w.png b/.tools/theme/PP_w.png
similarity index 100%
rename from .theme/PP_w.png
rename to .tools/theme/PP_w.png
diff --git a/.tmpl/github-markdown.css b/.tools/theme/github-markdown.css
similarity index 100%
rename from .tmpl/github-markdown.css
rename to .tools/theme/github-markdown.css
diff --git a/.tmpl/marked.js b/.tools/theme/marked.js
similarity index 100%
rename from .tmpl/marked.js
rename to .tools/theme/marked.js
diff --git a/01.fit_a_line/README.en.ipynb b/01.fit_a_line/README.en.ipynb
index a819dc5d0db3f7aa639834722ad024c1f22f49dc..a3f95c5ca96a7e6149c474d2ebb2c1d958bbe546 100644
--- a/01.fit_a_line/README.en.ipynb
+++ b/01.fit_a_line/README.en.ipynb
@@ -7,7 +7,7 @@
         "# Linear Regression\n",
         "Let us begin the tutorial with a classical problem called Linear Regression \\[[1](#References)\\]. In this chapter, we will train a model from a realistic dataset to predict home prices. Some important concepts in Machine Learning will be covered through this example.\n",
         "\n",
-        "The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).\n",
+        "The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).\n",
         "\n",
         "## Problem Setup\n",
         "Suppose we have a dataset of $n$ real estate properties. These real estate properties will be referred to as *homes* in this chapter for clarity.\n",
@@ -308,19 +308,41 @@
         "editable": true
       },
       "source": [
-        "# event_handler to print training and testing info\n",
+        "import matplotlib.pyplot as plt\n",
+        "from IPython import display\n",
+        "import cPickle\n",
+        "\n",
+        "step=0\n",
+        "\n",
+        "train_costs=[],[]\n",
+        "test_costs=[],[]\n",
+        "\n",
         "def event_handler(event):\n",
+        "    global step\n",
+        "    global train_costs\n",
+        "    global test_costs\n",
         "    if isinstance(event, paddle.event.EndIteration):\n",
-        "        if event.batch_id % 100 == 0:\n",
-        "            print \"Pass %d, Batch %d, Cost %f\" % (\n",
-        "                event.pass_id, event.batch_id, event.cost)\n",
-        "\n",
-        "    if isinstance(event, paddle.event.EndPass):\n",
-        "        result = trainer.test(\n",
-        "            reader=paddle.batch(\n",
-        "                uci_housing.test(), batch_size=2),\n",
-        "            feeding=feeding)\n",
-        "        print \"Test %d, Cost %f\" % (event.pass_id, result.cost)\n"
+        "        need_plot = False\n",
+        "        if step % 10 == 0:  # every 10 batches, record a train cost\n",
+        "            train_costs[0].append(step)\n",
+        "            train_costs[1].append(event.cost)\n",
+        "\n",
+        "        if step % 1000 == 0: # every 1000 batches, record a test cost\n",
+        "            result = trainer.test(\n",
+        "                reader=paddle.batch(\n",
+        "                    uci_housing.test(), batch_size=2),\n",
+        "                feeding=feeding)\n",
+        "            test_costs[0].append(step)\n",
+        "            test_costs[1].append(result.cost)\n",
+        "\n",
+        "        if step % 100 == 0: # every 100 batches, update cost plot\n",
+        "            plt.plot(*train_costs)\n",
+        "            plt.plot(*test_costs)\n",
+        "            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')\n",
+        "            display.clear_output(wait=True)\n",
+        "            display.display(plt.gcf())\n",
+        "            plt.gcf().clear()\n",
+        "        step += 1\n"
       ],
       "outputs": [
         {
@@ -372,6 +394,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
+        "\n",
+        "![png](./image/train-and-test.png)\n",
         "\n",
         "## Summary\n",
         "This chapter introduces *Linear Regression* and how to train and test this model with PaddlePaddle, using the UCI Housing Data Set. Because a large number of more complex models and techniques are derived from linear regression, it is important to understand its underlying theory and limitation.\n",
diff --git a/01.fit_a_line/README.en.md b/01.fit_a_line/README.en.md
index 67bff40b73d02b02e54a6e7d555b4fbe4984d23b..7f42b7da50adec54a779d388cec6572177dd88f3 100644
--- a/01.fit_a_line/README.en.md
+++ b/01.fit_a_line/README.en.md
@@ -1,7 +1,7 @@
 # Linear Regression
 Let us begin the tutorial with a classical problem called Linear Regression \[[1](#References)\]. In this chapter, we will train a model from a realistic dataset to predict home prices. Some important concepts in Machine Learning will be covered through this example.
 
-The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
+The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/book/blob/develop/README.en.md).
 
 ## Problem Setup
 Suppose we have a dataset of $n$ real estate properties. These real estate properties will be referred to as *homes* in this chapter for clarity.
@@ -163,19 +163,41 @@ feeding={'x': 0, 'y': 1}
 Moreover, an event handler is provided to print the training progress:
 
 ```python
-# event_handler to print training and testing info
+import matplotlib.pyplot as plt
+from IPython import display
+import cPickle
+
+step=0
+
+train_costs=[],[]
+test_costs=[],[]
+
 def event_handler(event):
+    global step
+    global train_costs
+    global test_costs
     if isinstance(event, paddle.event.EndIteration):
-        if event.batch_id % 100 == 0:
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.pass_id, event.batch_id, event.cost)
-
-    if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(
-            reader=paddle.batch(
-                uci_housing.test(), batch_size=2),
-            feeding=feeding)
-        print "Test %d, Cost %f" % (event.pass_id, result.cost)
+        need_plot = False
+        if step % 10 == 0:  # every 10 batches, record a train cost
+            train_costs[0].append(step)
+            train_costs[1].append(event.cost)
+
+        if step % 1000 == 0: # every 1000 batches, record a test cost
+            result = trainer.test(
+                reader=paddle.batch(
+                    uci_housing.test(), batch_size=2),
+                feeding=feeding)
+            test_costs[0].append(step)
+            test_costs[1].append(result.cost)
+
+        if step % 100 == 0: # every 100 batches, update cost plot
+            plt.plot(*train_costs)
+            plt.plot(*test_costs)
+            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')
+            display.clear_output(wait=True)
+            display.display(plt.gcf())
+            plt.gcf().clear()
+        step += 1
 ```
 
 ### Start Training
@@ -191,6 +213,8 @@ trainer.train(
     num_passes=30)
 ```
 
+![png](./image/train-and-test.png)
+
 ## Summary
 This chapter introduces *Linear Regression* and how to train and test this model with PaddlePaddle, using the UCI Housing Data Set. Because a large number of more complex models and techniques are derived from linear regression, it is important to understand its underlying theory and limitation.
 
diff --git a/01.fit_a_line/README.ipynb b/01.fit_a_line/README.ipynb
index 07f15fa38f330f55c63926888b2d732c486b2079..78666779bbf83d8469f18ab5d8cba17fd664919f 100644
--- a/01.fit_a_line/README.ipynb
+++ b/01.fit_a_line/README.ipynb
@@ -7,7 +7,7 @@
         "# 线性回归\n",
         "让我们从经典的线性回归（Linear Regression \\[[1](#参考文献)\\]）模型开始这份教程。在这一章里，你将使用真实的数据集建立起一个房价预测模型，并且了解到机器学习中的若干重要概念。\n",
         "\n",
-        "本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。\n",
+        "本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。\n",
         "\n",
         "## 背景介绍\n",
         "给定一个大小为$n$的数据集  ${\\{y_{i}, x_{i1}, ..., x_{id}\\}}_{i=1}^{n}$，其中$x_{i1}, \\ldots, x_{id}$是第$i$个样本$d$个属性上的取值，$y_i$是该样本待预测的目标。线性回归模型假设目标$y_i$可以被属性间的线性组合描述，即\n",
@@ -35,7 +35,7 @@
         "\n",
         "$\\hat{Y}$ 表示模型的预测结果，用来和真实值$Y$区分。模型要学习的参数即：$\\omega_1, \\ldots, \\omega_{13}, b$。\n",
         "\n",
-        "建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\\hat{y_{i}}$，损失函数输出一个非负的实值。这个实质通常用来反映模型误差的大小。\n",
+        "建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\\hat{y_{i}}$，损失函数输出一个非负的实值。这个实值通常用来反映模型误差的大小。\n",
         "\n",
         "对于线性回归模型来讲，最常见的损失函数就是均方误差（Mean Squared Error， [MSE](https://en.wikipedia.org/wiki/Mean_squared_error)）了，它的形式是：\n",
         "\n",
@@ -304,18 +304,41 @@
       },
       "source": [
         "# event_handler to print training and testing info\n",
+        "import matplotlib.pyplot as plt\n",
+        "from IPython import display\n",
+        "import cPickle\n",
+        "\n",
+        "step=0\n",
+        "\n",
+        "train_costs=[],[]\n",
+        "test_costs=[],[]\n",
+        "\n",
         "def event_handler(event):\n",
+        "    global step\n",
+        "    global train_costs\n",
+        "    global test_costs\n",
         "    if isinstance(event, paddle.event.EndIteration):\n",
-        "        if event.batch_id % 100 == 0:\n",
-        "            print \"Pass %d, Batch %d, Cost %f\" % (\n",
-        "                event.pass_id, event.batch_id, event.cost)\n",
-        "\n",
-        "    if isinstance(event, paddle.event.EndPass):\n",
-        "        result = trainer.test(\n",
-        "            reader=paddle.batch(\n",
-        "                uci_housing.test(), batch_size=2),\n",
-        "            feeding=feeding)\n",
-        "        print \"Test %d, Cost %f\" % (event.pass_id, result.cost)\n"
+        "        need_plot = False\n",
+        "        if step % 10 == 0:  # every 10 batches, record a train cost\n",
+        "            train_costs[0].append(step)\n",
+        "            train_costs[1].append(event.cost)\n",
+        "\n",
+        "        if step % 1000 == 0: # every 1000 batches, record a test cost\n",
+        "            result = trainer.test(\n",
+        "                reader=paddle.batch(\n",
+        "                    uci_housing.test(), batch_size=2),\n",
+        "                feeding=feeding)\n",
+        "            test_costs[0].append(step)\n",
+        "            test_costs[1].append(result.cost)\n",
+        "\n",
+        "        if step % 100 == 0: # every 100 batches, update cost plot\n",
+        "            plt.plot(*train_costs)\n",
+        "            plt.plot(*test_costs)\n",
+        "            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')\n",
+        "            display.clear_output(wait=True)\n",
+        "            display.display(plt.gcf())\n",
+        "            plt.gcf().clear()\n",
+        "        step += 1\n"
       ],
       "outputs": [
         {
@@ -367,6 +390,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
+        "\n",
+        "![png](./image/train-and-test.png)\n",
         "\n",
         "## 总结\n",
         "在这章里，我们借助波士顿房价这一数据集，介绍了线性回归模型的基本概念，以及如何使用PaddlePaddle实现训练和测试的过程。很多的模型和技巧都是从简单的线性回归模型演化而来，因此弄清楚线性模型的原理和局限非常重要。\n",
diff --git a/01.fit_a_line/README.md b/01.fit_a_line/README.md
index b4516851e7e106750740557ccfbf31c8f1e4f5d0..2c3f1fd4dd61aec8ad6e97881d6229f4e6ef91b1 100644
--- a/01.fit_a_line/README.md
+++ b/01.fit_a_line/README.md
@@ -1,7 +1,7 @@
 # 线性回归
 让我们从经典的线性回归（Linear Regression \[[1](#参考文献)\]）模型开始这份教程。在这一章里，你将使用真实的数据集建立起一个房价预测模型，并且了解到机器学习中的若干重要概念。
 
-本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/book/blob/develop/README.md)。
 
 ## 背景介绍
 给定一个大小为$n$的数据集  ${\{y_{i}, x_{i1}, ..., x_{id}\}}_{i=1}^{n}$，其中$x_{i1}, \ldots, x_{id}$是第$i$个样本$d$个属性上的取值，$y_i$是该样本待预测的目标。线性回归模型假设目标$y_i$可以被属性间的线性组合描述，即
@@ -29,7 +29,7 @@ $$\hat{Y} = \omega_1X_{1} + \omega_2X_{2} + \ldots + \omega_{13}X_{13} + b$$
 
 $\hat{Y}$ 表示模型的预测结果，用来和真实值$Y$区分。模型要学习的参数即：$\omega_1, \ldots, \omega_{13}, b$。
 
-建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\hat{y_{i}}$，损失函数输出一个非负的实值。这个实质通常用来反映模型误差的大小。
+建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\hat{y_{i}}$，损失函数输出一个非负的实值。这个实值通常用来反映模型误差的大小。
 
 对于线性回归模型来讲，最常见的损失函数就是均方误差（Mean Squared Error， [MSE](https://en.wikipedia.org/wiki/Mean_squared_error)）了，它的形式是：
 
@@ -159,18 +159,41 @@ feeding={'x': 0, 'y': 1}
 
 ```python
 # event_handler to print training and testing info
+import matplotlib.pyplot as plt
+from IPython import display
+import cPickle
+
+step=0
+
+train_costs=[],[]
+test_costs=[],[]
+
 def event_handler(event):
+    global step
+    global train_costs
+    global test_costs
     if isinstance(event, paddle.event.EndIteration):
-        if event.batch_id % 100 == 0:
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.pass_id, event.batch_id, event.cost)
-
-    if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(
-            reader=paddle.batch(
-                uci_housing.test(), batch_size=2),
-            feeding=feeding)
-        print "Test %d, Cost %f" % (event.pass_id, result.cost)
+        need_plot = False
+        if step % 10 == 0:  # every 10 batches, record a train cost
+            train_costs[0].append(step)
+            train_costs[1].append(event.cost)
+
+        if step % 1000 == 0: # every 1000 batches, record a test cost
+            result = trainer.test(
+                reader=paddle.batch(
+                    uci_housing.test(), batch_size=2),
+                feeding=feeding)
+            test_costs[0].append(step)
+            test_costs[1].append(result.cost)
+
+        if step % 100 == 0: # every 100 batches, update cost plot
+            plt.plot(*train_costs)
+            plt.plot(*test_costs)
+            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')
+            display.clear_output(wait=True)
+            display.display(plt.gcf())
+            plt.gcf().clear()
+        step += 1
 ```
 
 ### 开始训练
@@ -186,6 +209,8 @@ trainer.train(
     num_passes=30)
 ```
 
+![png](./image/train-and-test.png)
+
 ## 总结
 在这章里，我们借助波士顿房价这一数据集，介绍了线性回归模型的基本概念，以及如何使用PaddlePaddle实现训练和测试的过程。很多的模型和技巧都是从简单的线性回归模型演化而来，因此弄清楚线性模型的原理和局限非常重要。
 
diff --git a/01.fit_a_line/image/train-and-test.png b/01.fit_a_line/image/train-and-test.png
new file mode 100644
index 0000000000000000000000000000000000000000..bcd304a6a0baf30ecfbc43e08fc0aca179d05958
Binary files /dev/null and b/01.fit_a_line/image/train-and-test.png differ
diff --git a/01.fit_a_line/index.en.html b/01.fit_a_line/index.en.html
index 0c8fe2e9afc637fe889270d960bd5a1e234df9cf..06f5559174c252eaf951211d86ce86c7897d9ed9 100644
--- a/01.fit_a_line/index.en.html
+++ b/01.fit_a_line/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -43,7 +43,7 @@
 # Linear Regression
 Let us begin the tutorial with a classical problem called Linear Regression \[[1](#References)\]. In this chapter, we will train a model from a realistic dataset to predict home prices. Some important concepts in Machine Learning will be covered through this example.
 
-The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
+The source code for this tutorial lives on [book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line). For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/book/blob/develop/README.en.md).
 
 ## Problem Setup
 Suppose we have a dataset of $n$ real estate properties. These real estate properties will be referred to as *homes* in this chapter for clarity.
@@ -205,19 +205,41 @@ feeding={'x': 0, 'y': 1}
 Moreover, an event handler is provided to print the training progress:
 
 ```python
-# event_handler to print training and testing info
+import matplotlib.pyplot as plt
+from IPython import display
+import cPickle
+
+step=0
+
+train_costs=[],[]
+test_costs=[],[]
+
 def event_handler(event):
+    global step
+    global train_costs
+    global test_costs
     if isinstance(event, paddle.event.EndIteration):
-        if event.batch_id % 100 == 0:
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.pass_id, event.batch_id, event.cost)
-
-    if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(
-            reader=paddle.batch(
-                uci_housing.test(), batch_size=2),
-            feeding=feeding)
-        print "Test %d, Cost %f" % (event.pass_id, result.cost)
+        need_plot = False
+        if step % 10 == 0:  # every 10 batches, record a train cost
+            train_costs[0].append(step)
+            train_costs[1].append(event.cost)
+
+        if step % 1000 == 0: # every 1000 batches, record a test cost
+            result = trainer.test(
+                reader=paddle.batch(
+                    uci_housing.test(), batch_size=2),
+                feeding=feeding)
+            test_costs[0].append(step)
+            test_costs[1].append(result.cost)
+
+        if step % 100 == 0: # every 100 batches, update cost plot
+            plt.plot(*train_costs)
+            plt.plot(*test_costs)
+            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')
+            display.clear_output(wait=True)
+            display.display(plt.gcf())
+            plt.gcf().clear()
+        step += 1
 ```
 
 ### Start Training
@@ -233,6 +255,8 @@ trainer.train(
     num_passes=30)
 ```
 
+![png](./image/train-and-test.png)
+
 ## Summary
 This chapter introduces *Linear Regression* and how to train and test this model with PaddlePaddle, using the UCI Housing Data Set. Because a large number of more complex models and techniques are derived from linear regression, it is important to understand its underlying theory and limitation.
 
diff --git a/01.fit_a_line/index.html b/01.fit_a_line/index.html
index efa0cc70e3671fa049e75798ef73268a5feaca28..a866e13bf3321c22973198d8ae639327348c4587 100644
--- a/01.fit_a_line/index.html
+++ b/01.fit_a_line/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -43,7 +43,7 @@
 # 线性回归
 让我们从经典的线性回归（Linear Regression \[[1](#参考文献)\]）模型开始这份教程。在这一章里，你将使用真实的数据集建立起一个房价预测模型，并且了解到机器学习中的若干重要概念。
 
-本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/fit_a_line](https://github.com/PaddlePaddle/book/tree/develop/01.fit_a_line)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/book/blob/develop/README.md)。
 
 ## 背景介绍
 给定一个大小为$n$的数据集  ${\{y_{i}, x_{i1}, ..., x_{id}\}}_{i=1}^{n}$，其中$x_{i1}, \ldots, x_{id}$是第$i$个样本$d$个属性上的取值，$y_i$是该样本待预测的目标。线性回归模型假设目标$y_i$可以被属性间的线性组合描述，即
@@ -71,7 +71,7 @@ $$\hat{Y} = \omega_1X_{1} + \omega_2X_{2} + \ldots + \omega_{13}X_{13} + b$$
 
 $\hat{Y}$ 表示模型的预测结果，用来和真实值$Y$区分。模型要学习的参数即：$\omega_1, \ldots, \omega_{13}, b$。
 
-建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\hat{y_{i}}$，损失函数输出一个非负的实值。这个实质通常用来反映模型误差的大小。
+建立模型后，我们需要给模型一个优化目标，使得学到的参数能够让预测值$\hat{Y}$尽可能地接近真实值$Y$。这里我们引入损失函数（[Loss Function](https://en.wikipedia.org/wiki/Loss_function)，或Cost Function）这个概念。 输入任意一个数据样本的目标值$y_{i}$和模型给出的预测值$\hat{y_{i}}$，损失函数输出一个非负的实值。这个实值通常用来反映模型误差的大小。
 
 对于线性回归模型来讲，最常见的损失函数就是均方误差（Mean Squared Error， [MSE](https://en.wikipedia.org/wiki/Mean_squared_error)）了，它的形式是：
 
@@ -201,18 +201,41 @@ feeding={'x': 0, 'y': 1}
 
 ```python
 # event_handler to print training and testing info
+import matplotlib.pyplot as plt
+from IPython import display
+import cPickle
+
+step=0
+
+train_costs=[],[]
+test_costs=[],[]
+
 def event_handler(event):
+    global step
+    global train_costs
+    global test_costs
     if isinstance(event, paddle.event.EndIteration):
-        if event.batch_id % 100 == 0:
-            print "Pass %d, Batch %d, Cost %f" % (
-                event.pass_id, event.batch_id, event.cost)
-
-    if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(
-            reader=paddle.batch(
-                uci_housing.test(), batch_size=2),
-            feeding=feeding)
-        print "Test %d, Cost %f" % (event.pass_id, result.cost)
+        need_plot = False
+        if step % 10 == 0:  # every 10 batches, record a train cost
+            train_costs[0].append(step)
+            train_costs[1].append(event.cost)
+
+        if step % 1000 == 0: # every 1000 batches, record a test cost
+            result = trainer.test(
+                reader=paddle.batch(
+                    uci_housing.test(), batch_size=2),
+                feeding=feeding)
+            test_costs[0].append(step)
+            test_costs[1].append(result.cost)
+
+        if step % 100 == 0: # every 100 batches, update cost plot
+            plt.plot(*train_costs)
+            plt.plot(*test_costs)
+            plt.legend(['Train Cost', 'Test Cost'], loc='upper left')
+            display.clear_output(wait=True)
+            display.display(plt.gcf())
+            plt.gcf().clear()
+        step += 1
 ```
 
 ### 开始训练
@@ -228,6 +251,8 @@ trainer.train(
     num_passes=30)
 ```
 
+![png](./image/train-and-test.png)
+
 ## 总结
 在这章里，我们借助波士顿房价这一数据集，介绍了线性回归模型的基本概念，以及如何使用PaddlePaddle实现训练和测试的过程。很多的模型和技巧都是从简单的线性回归模型演化而来，因此弄清楚线性模型的原理和局限非常重要。
 
diff --git a/02.recognize_digits/README.en.md b/02.recognize_digits/README.en.md
index 98ce6158439f61d1e5a4337c58f3e6027fa8fea7..15a70e75af4caa39f32d7b4db4233fc080a17eed 100644
--- a/02.recognize_digits/README.en.md
+++ b/02.recognize_digits/README.en.md
@@ -1,6 +1,6 @@
 # Recognize Digits
 
-The source code for this tutorial is under [book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/recognize_digits). First-time readers, please refer to PaddlePaddle [installation instructions](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
+The source code for this tutorial is under [book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/02.recognize_digits). First-time readers, please refer to PaddlePaddle [installation instructions](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
 ## Introduction
 When we learn a new programming language, the first task is usually to write a program that prints "Hello World." In Machine Learning or Deep Learning, the equivalent task is to train a model to perform handwritten digit recognition with [MNIST](http://yann.lecun.com/exdb/mnist/) dataset. Handwriting recognition is a typical image classification problem. The problem is relatively easy, and MNIST is a complete dataset. As a simple Computer Vision dataset, MNIST contains images of handwritten digits and their corresponding labels (Fig. 1). The input image is a 28x28 matrix, and the label is one of the digits from 0 to 9. Each image is normalized in size and centered.
@@ -12,7 +12,7 @@ Fig. 1. Examples of MNIST images
 
 The MNIST dataset is created from the [NIST](https://www.nist.gov/srd/nist-special-database-19) Special Database 3 (SD-3) and the Special Database 1 (SD-1). The SD-3 is labeled by the staff of the U.S. Census Bureau, while SD-1 is labeled by high school students the in U.S. Therefore the SD-3 is cleaner and easier to recognize than the SD-1 dataset. Yann LeCun et al. used half of the samples from each of SD-1 and SD-3 to create the MNIST training set (60,000 samples) and test set (10,000 samples), where training set was labeled by 250 different annotators, and it was guaranteed that there wasn't a complete overlap of annotators of training set and test set.
 
-Yann LeCun, one of the founders of Deep Learning, contributed highly towards handwritten character recognition in early days and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for handwritten characters. CNNs are now a critical concept in Deep Learning. From Yann LeCun's first proposal of LeNet to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification) tutorial), CNN achieved a series of impressive results in Image Classification tasks.
+Yann LeCun, one of the founders of Deep Learning, contributed highly towards handwritten character recognition in early days and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for handwritten characters. CNNs are now a critical concept in Deep Learning. From Yann LeCun's first proposal of LeNet to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification) tutorial), CNN achieved a series of impressive results in Image Classification tasks.
 
 Many algorithms are tested on MNIST. In 1998, LeCun experimented with single layer linear classifier, MLP (Multilayer Perceptron) and Multilayer CNN LeNet. These algorithms constantly reduced test error from 12% to 0.7% \[[1](#References)\]. Since then, researchers have worked on many algorithms such as k-NN (K-Nearest Neighbors) \[[2](#References)\], Support Vector Machine (SVM) \[[3](#References)\], Neural Networks \[[4-7](#References)\] and Boosting \[[8](#References)\]. Various preprocessing methods like distortion removal, noise removal, blurring etc. have also been applied to increase recognition accuracy.
 
diff --git a/02.recognize_digits/README.md b/02.recognize_digits/README.md
index cb78486c027a615e5d96373256ba602509899396..85f0defa1989b3832a50564e46274ae7270bed60 100644
--- a/02.recognize_digits/README.md
+++ b/02.recognize_digits/README.md
@@ -1,6 +1,6 @@
 # 识别数字
 
-本教程源代码目录在[book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/recognize_digits)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/02.recognize_digits)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 当我们学习编程的时候，编写的第一个程序一般是实现打印"Hello World"。而机器学习（或深度学习）的入门教程，一般都是 [MNIST](http://yann.lecun.com/exdb/mnist/) 数据库上的手写识别问题。原因是手写识别属于典型的图像分类问题，比较简单，同时MNIST数据集也很完备。MNIST数据集作为一个简单的计算机视觉数据集，包含一系列如图1所示的手写数字图片和对应的标签。图片是28x28的像素矩阵，标签则对应着0~9的10个数字。每张图片都经过了大小归一化和居中处理。
@@ -12,7 +12,7 @@
 
 MNIST数据集是从 [NIST](https://www.nist.gov/srd/nist-special-database-19) 的Special Database 3（SD-3）和Special Database 1（SD-1）构建而来。由于SD-3是由美国人口调查局的员工进行标注，SD-1是由美国高中生进行标注，因此SD-3比SD-1更干净也更容易识别。Yann LeCun等人从SD-1和SD-3中各取一半作为MNIST的训练集（60000条数据）和测试集（10000条数据），其中训练集来自250位不同的标注员，此外还保证了训练集和测试集的标注员是不完全相同的。
 
-Yann LeCun早先在手写字符识别上做了很多研究，并在研究过程中提出了卷积神经网络（Convolutional Neural Network），大幅度地提高了手写字符的识别能力，也因此成为了深度学习领域的奠基人之一。如今的深度学习领域，卷积神经网络占据了至关重要的地位，从最早Yann LeCun提出的简单LeNet，到如今ImageNet大赛上的优胜模型VGGNet、GoogLeNet、ResNet等（请参见[图像分类](https://github.com/PaddlePaddle/book/tree/develop/image_classification) 教程），人们在图像分类领域，利用卷积神经网络得到了一系列惊人的结果。
+Yann LeCun早先在手写字符识别上做了很多研究，并在研究过程中提出了卷积神经网络（Convolutional Neural Network），大幅度地提高了手写字符的识别能力，也因此成为了深度学习领域的奠基人之一。如今的深度学习领域，卷积神经网络占据了至关重要的地位，从最早Yann LeCun提出的简单LeNet，到如今ImageNet大赛上的优胜模型VGGNet、GoogLeNet、ResNet等（请参见[图像分类](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification) 教程），人们在图像分类领域，利用卷积神经网络得到了一系列惊人的结果。
 
 有很多算法在MNIST上进行实验。1998年，LeCun分别用单层线性分类器、多层感知器（Multilayer Perceptron, MLP）和多层卷积神经网络LeNet进行实验，使得测试集上的误差不断下降（从12%下降到0.7%）\[[1](#参考文献)\]。此后，科学家们又基于K近邻（K-Nearest Neighbors）算法\[[2](#参考文献)\]、支持向量机（SVM）\[[3](#参考文献)\]、神经网络\[[4-7](#参考文献)\]和Boosting方法\[[8](#参考文献)\]等做了大量实验，并采用多种预处理方法（如去除歪曲、去噪、模糊等）来提高识别的准确率。
 
@@ -36,7 +36,7 @@ $$ y_i = \text{softmax}(\sum_j W_{i,j}x_j + b_i) $$
 
 其中 $ \text{softmax}(x_i) = \frac{e^{x_i}}{\sum_j e^{x_j}} $
 
-对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维输入特征经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
+对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维结果向量经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
 
 在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy），公式如下：
 
diff --git a/02.recognize_digits/index.en.html b/02.recognize_digits/index.en.html
index 62b49dfdd6442858ff13593e5f77d9d2deba518d..03960fd4b38172a6b821c9b612a7d7c2034bd8a2 100644
--- a/02.recognize_digits/index.en.html
+++ b/02.recognize_digits/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # Recognize Digits
 
-The source code for this tutorial is under [book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/recognize_digits). First-time readers, please refer to PaddlePaddle [installation instructions](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
+The source code for this tutorial is under [book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/02.recognize_digits). First-time readers, please refer to PaddlePaddle [installation instructions](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
 ## Introduction
 When we learn a new programming language, the first task is usually to write a program that prints "Hello World." In Machine Learning or Deep Learning, the equivalent task is to train a model to perform handwritten digit recognition with [MNIST](http://yann.lecun.com/exdb/mnist/) dataset. Handwriting recognition is a typical image classification problem. The problem is relatively easy, and MNIST is a complete dataset. As a simple Computer Vision dataset, MNIST contains images of handwritten digits and their corresponding labels (Fig. 1). The input image is a 28x28 matrix, and the label is one of the digits from 0 to 9. Each image is normalized in size and centered.
@@ -54,7 +54,7 @@ Fig. 1. Examples of MNIST images
 
 The MNIST dataset is created from the [NIST](https://www.nist.gov/srd/nist-special-database-19) Special Database 3 (SD-3) and the Special Database 1 (SD-1). The SD-3 is labeled by the staff of the U.S. Census Bureau, while SD-1 is labeled by high school students the in U.S. Therefore the SD-3 is cleaner and easier to recognize than the SD-1 dataset. Yann LeCun et al. used half of the samples from each of SD-1 and SD-3 to create the MNIST training set (60,000 samples) and test set (10,000 samples), where training set was labeled by 250 different annotators, and it was guaranteed that there wasn't a complete overlap of annotators of training set and test set.
 
-Yann LeCun, one of the founders of Deep Learning, contributed highly towards handwritten character recognition in early days and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for handwritten characters. CNNs are now a critical concept in Deep Learning. From Yann LeCun's first proposal of LeNet to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification) tutorial), CNN achieved a series of impressive results in Image Classification tasks.
+Yann LeCun, one of the founders of Deep Learning, contributed highly towards handwritten character recognition in early days and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for handwritten characters. CNNs are now a critical concept in Deep Learning. From Yann LeCun's first proposal of LeNet to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification) tutorial), CNN achieved a series of impressive results in Image Classification tasks.
 
 Many algorithms are tested on MNIST. In 1998, LeCun experimented with single layer linear classifier, MLP (Multilayer Perceptron) and Multilayer CNN LeNet. These algorithms constantly reduced test error from 12% to 0.7% \[[1](#References)\]. Since then, researchers have worked on many algorithms such as k-NN (K-Nearest Neighbors) \[[2](#References)\], Support Vector Machine (SVM) \[[3](#References)\], Neural Networks \[[4-7](#References)\] and Boosting \[[8](#References)\]. Various preprocessing methods like distortion removal, noise removal, blurring etc. have also been applied to increase recognition accuracy.
 
diff --git a/02.recognize_digits/index.html b/02.recognize_digits/index.html
index 9ed4d220920437cbd5699e62b5686bc44a466eeb..3b45d841952289b2fcd11ae149538596a5dd6a1f 100644
--- a/02.recognize_digits/index.html
+++ b/02.recognize_digits/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # 识别数字
 
-本教程源代码目录在[book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/recognize_digits)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/recognize_digits](https://github.com/PaddlePaddle/book/tree/develop/02.recognize_digits)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 当我们学习编程的时候，编写的第一个程序一般是实现打印"Hello World"。而机器学习（或深度学习）的入门教程，一般都是 [MNIST](http://yann.lecun.com/exdb/mnist/) 数据库上的手写识别问题。原因是手写识别属于典型的图像分类问题，比较简单，同时MNIST数据集也很完备。MNIST数据集作为一个简单的计算机视觉数据集，包含一系列如图1所示的手写数字图片和对应的标签。图片是28x28的像素矩阵，标签则对应着0~9的10个数字。每张图片都经过了大小归一化和居中处理。
@@ -54,7 +54,7 @@
 
 MNIST数据集是从 [NIST](https://www.nist.gov/srd/nist-special-database-19) 的Special Database 3（SD-3）和Special Database 1（SD-1）构建而来。由于SD-3是由美国人口调查局的员工进行标注，SD-1是由美国高中生进行标注，因此SD-3比SD-1更干净也更容易识别。Yann LeCun等人从SD-1和SD-3中各取一半作为MNIST的训练集（60000条数据）和测试集（10000条数据），其中训练集来自250位不同的标注员，此外还保证了训练集和测试集的标注员是不完全相同的。
 
-Yann LeCun早先在手写字符识别上做了很多研究，并在研究过程中提出了卷积神经网络（Convolutional Neural Network），大幅度地提高了手写字符的识别能力，也因此成为了深度学习领域的奠基人之一。如今的深度学习领域，卷积神经网络占据了至关重要的地位，从最早Yann LeCun提出的简单LeNet，到如今ImageNet大赛上的优胜模型VGGNet、GoogLeNet、ResNet等（请参见[图像分类](https://github.com/PaddlePaddle/book/tree/develop/image_classification) 教程），人们在图像分类领域，利用卷积神经网络得到了一系列惊人的结果。
+Yann LeCun早先在手写字符识别上做了很多研究，并在研究过程中提出了卷积神经网络（Convolutional Neural Network），大幅度地提高了手写字符的识别能力，也因此成为了深度学习领域的奠基人之一。如今的深度学习领域，卷积神经网络占据了至关重要的地位，从最早Yann LeCun提出的简单LeNet，到如今ImageNet大赛上的优胜模型VGGNet、GoogLeNet、ResNet等（请参见[图像分类](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification) 教程），人们在图像分类领域，利用卷积神经网络得到了一系列惊人的结果。
 
 有很多算法在MNIST上进行实验。1998年，LeCun分别用单层线性分类器、多层感知器（Multilayer Perceptron, MLP）和多层卷积神经网络LeNet进行实验，使得测试集上的误差不断下降（从12%下降到0.7%）\[[1](#参考文献)\]。此后，科学家们又基于K近邻（K-Nearest Neighbors）算法\[[2](#参考文献)\]、支持向量机（SVM）\[[3](#参考文献)\]、神经网络\[[4-7](#参考文献)\]和Boosting方法\[[8](#参考文献)\]等做了大量实验，并采用多种预处理方法（如去除歪曲、去噪、模糊等）来提高识别的准确率。
 
@@ -78,7 +78,7 @@ $$ y_i = \text{softmax}(\sum_j W_{i,j}x_j + b_i) $$
 
 其中 $ \text{softmax}(x_i) = \frac{e^{x_i}}{\sum_j e^{x_j}} $
 
-对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维输入特征经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
+对于有 $N$ 个类别的多分类问题，指定 $N$ 个输出节点，$N$ 维结果向量经过softmax将归一化为 $N$ 个[0,1]范围内的实数值，分别表示该样本属于这 $N$ 个类别的概率。此处的 $y_i$ 即对应该图片为数字 $i$ 的预测概率。
 
 在分类问题中，我们一般采用交叉熵代价损失函数（cross entropy），公式如下：
 
diff --git a/03.image_classification/README.en.md b/03.image_classification/README.en.md
index db73fb6951a2c586ff8a29371b9055c82b59a069..0bb0775eaa3f689b4646e854cf5d6dd9f6d72263 100644
--- a/03.image_classification/README.en.md
+++ b/03.image_classification/README.en.md
@@ -1,7 +1,7 @@
 Image Classification
 =======================
 
-The source code for this chapter is at [book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification). First-time users, please refer to PaddlePaddle [Installation Tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) for installation instructions.
+The source code for this chapter is at [book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification). First-time users, please refer to PaddlePaddle [Installation Tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) for installation instructions.
 
 ## Background
 
diff --git a/03.image_classification/README.md b/03.image_classification/README.md
index 6236f13b0269d9495a0c415ff9e6ec7d92d1b1fa..e97cb3365591320bef7c2dd167a7b81fd79e46be 100644
--- a/03.image_classification/README.md
+++ b/03.image_classification/README.md
@@ -1,6 +1,6 @@
 # 图像分类
 
-本教程源代码目录在[book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/03.image_classification/index.en.html b/03.image_classification/index.en.html
index 5a870bcfd69bd62423fc422a60da16f463334b7b..4e4b413ab81a5b14702b2338040f2ad60fc27f33 100644
--- a/03.image_classification/index.en.html
+++ b/03.image_classification/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -43,7 +43,7 @@
 Image Classification
 =======================
 
-The source code for this chapter is at [book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification). First-time users, please refer to PaddlePaddle [Installation Tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) for installation instructions.
+The source code for this chapter is at [book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification). First-time users, please refer to PaddlePaddle [Installation Tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) for installation instructions.
 
 ## Background
 
diff --git a/03.image_classification/index.html b/03.image_classification/index.html
index 834b6506026f97cc6fa08fde070353ad54f8020c..6c178be6bb8e4ae60ba033be1505101413636128 100644
--- a/03.image_classification/index.html
+++ b/03.image_classification/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # 图像分类
 
-本教程源代码目录在[book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/image_classification](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/04.word2vec/README.en.md b/04.word2vec/README.en.md
index 4c1ba71137e21d2a980bc0fda1ac3be6b158b7e2..53cdd509bd064c352207f30129586d792a0862e2 100644
--- a/04.word2vec/README.en.md
+++ b/04.word2vec/README.en.md
@@ -1,6 +1,6 @@
 # Word2Vec
 
-This is intended as a reference tutorial. The source code of this tutorial lives on [book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/word2vec).
+This is intended as a reference tutorial. The source code of this tutorial lives on [book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/04.word2vec).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
diff --git a/04.word2vec/README.md b/04.word2vec/README.md
index eaf1feb77417307f9cb925240bad836631f22e09..872aeec60aed997d6cd54c9ccaa8f72b2b8b30cf 100644
--- a/04.word2vec/README.md
+++ b/04.word2vec/README.md
@@ -1,7 +1,7 @@
 
 # 词向量
 
-本教程源代码目录在[book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/word2vec)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/04.word2vec)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/04.word2vec/index.en.html b/04.word2vec/index.en.html
index 1a4940012a583d422238336b712c8342b7a023eb..307c72f430735d188e2078f43b09ed11e9edca66 100644
--- a/04.word2vec/index.en.html
+++ b/04.word2vec/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # Word2Vec
 
-This is intended as a reference tutorial. The source code of this tutorial lives on [book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/word2vec).
+This is intended as a reference tutorial. The source code of this tutorial lives on [book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/04.word2vec).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
diff --git a/04.word2vec/index.html b/04.word2vec/index.html
index ebc7d4f47d8bfb783be55df2723d7b057537506d..8fa126f5a8dd0497208cfd05b05e0faf6d18686e 100644
--- a/04.word2vec/index.html
+++ b/04.word2vec/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -43,7 +43,7 @@
 
 # 词向量
 
-本教程源代码目录在[book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/word2vec)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/word2vec](https://github.com/PaddlePaddle/book/tree/develop/04.word2vec)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/05.understand_sentiment/README.en.md b/05.understand_sentiment/README.en.md
index 8fe8a59d26b831b907d199fb060e91fb59a92848..1816473b7902a90638a30d3640fbe05e165b3d27 100644
--- a/05.understand_sentiment/README.en.md
+++ b/05.understand_sentiment/README.en.md
@@ -89,17 +89,17 @@ o_t & = \sigma(W_{xo}x_t+W_{ho}h_{h-1}+W_{co}c_{t}+b_o)\\\\
 h_t & = o_t\odot \tanh(c_t)\\\\
 \end{align}
 
-In the equation，$i_t, f_t, c_t, o_t$ stand for input gate, forget gate, memory cell and output gate, respectively. $W$ and $b$ are model parameters, $\tanh$ is a hyperbolic tangent, and $\odot$ denotes an element-wise product operation. The input gate controls the magnitude of the new input into the memory cell $c$; the forget gate controls the memory propagated from the last time step; the output gate controls the magnitutde of the output. The three gates are computed similarly with different parameters, and they influence memory cell $c$ separately, as shown in Figure 3:
+In the equation，$i_t, f_t, c_t, o_t$ stand for input gate, forget gate, memory cell and output gate, respectively. $W$ and $b$ are model parameters, $\tanh$ is a hyperbolic tangent, and $\odot$ denotes an element-wise product operation. The input gate controls the magnitude of the new input into the memory cell $c$; the forget gate controls the memory propagated from the last time step; the output gate controls the magnitude of the output. The three gates are computed similarly with different parameters, and they influence memory cell $c$ separately, as shown in Figure 3:
 
 <p align="center">
 <img src="image/lstm_en.png" width = "65%" align="center"/><br/>
 Figure 3. LSTM at time step $t$ [7].
 </p>
 
-LSTM enhances the ability of considering long-term reliance, with the help of memory cell and gate. Similar structures are also proposed in Gated Recurrent Unit (GRU)\[[8](Reference)\] with simpler design. **The structures are still similar to RNN, though with some modifications (As shown in Figure 2), i.e., latent status depends on input as well as the latent status of last time-step, and the process goes on recurrently until all input are consumed:**
+Similar to LSTM, other structures with memory cell and gates also enhance the network's long-term reliance. One such example is the **Gated Recurrent Unit**(GRU)\[[8](Reference)\. The structures are still similar to RNNs (as shown in Figure 2) in the following way: its latent status depends on both the current input as well as the latent status from the last time-step, and the process goes on recurrently until all the inputs are consumed:
 
-$$ h_t=Recrurent(x_t,h_{t-1})$$
-where $Recrurent$ is a simple RNN, GRU or LSTM.
+$$ h_t=Recurrent(x_t,h_{t-1})$$
+where $Recurrent$ is a simple RNN, GRU or LSTM.
 
 ### Stacked Bidirectional LSTM
 
diff --git a/05.understand_sentiment/README.md b/05.understand_sentiment/README.md
index 3da65a419c0bc4146d2c2b55c4d446ef93706a8d..891461e1d1be987515c5f58888ad36f41bc2d7c7 100644
--- a/05.understand_sentiment/README.md
+++ b/05.understand_sentiment/README.md
@@ -1,8 +1,9 @@
 # 情感分析
 
-本教程源代码目录在[book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
+
 在自然语言处理中，情感分析一般是指判断一段文本所表达的情绪状态。其中，一段文本可以是一个句子，一个段落或一个文档。情绪状态可以是两类，如（正面，负面），（高兴，悲伤）；也可以是三类，如（积极，消极，中性）等等。情感分析的应用场景十分广泛，如把用户在购物网站（亚马逊、天猫、淘宝等）、旅游网站、电影评论网站上发表的评论分成正面评论和负面评论；或为了分析用户对于某一产品的整体使用感受，抓取产品的用户评论并进行情感分析等等。表格1展示了对电影评论进行情感分析的例子：
 
 | 电影评论       | 类别  |
@@ -19,16 +20,22 @@
 对于一段文本，BOW表示会忽略其词顺序、语法和句法，将这段文本仅仅看做是一个词集合，因此BOW方法并不能充分表示文本的语义信息。例如，句子“这部电影糟糕透了”和“一个乏味，空洞，没有内涵的作品”在情感分析中具有很高的语义相似度，但是它们的BOW表示的相似度为0。又如，句子“一个空洞，没有内涵的作品”和“一个不空洞而且有内涵的作品”的BOW相似度很高，但实际上它们的意思很不一样。  
 
 本章我们所要介绍的深度学习模型克服了BOW表示的上述缺陷，它在考虑词顺序的基础上把文本映射到低维度的语义空间，并且以端对端（end to end）的方式进行文本表示及分类，其性能相对于传统方法有显著的提升\[[1](#参考文献)\]。
+
 ## 模型概览
+
 本章所使用的文本表示模型为卷积神经网络（Convolutional Neural Networks）和循环神经网络(Recurrent Neural Networks)及其扩展。下面依次介绍这几个模型。
+
 ### 文本卷积神经网络（CNN）
+
 卷积神经网络经常用来处理具有类似网格拓扑结构（grid-like topology）的数据。例如，图像可以视为二维网格的像素点，自然语言可以视为一维的词序列。卷积神经网络可以提取多种局部特征，并对其进行组合抽象得到更高级的特征表示。实验表明，卷积神经网络能高效地对图像及文本问题进行建模处理。  
 
 卷积神经网络主要由卷积（convolution）和池化（pooling）操作构成，其应用及组合方式灵活多变，种类繁多。本小结我们以一种简单的文本分类卷积神经网络为例进行讲解\[[1](#参考文献)\]，如图1所示：
+
 <p align="center">
 <img src="image/text_cnn.png" width = "80%" align="center"/><br/>
 图1. 卷积神经网络文本分类模型
 </p>
+
 假设待处理句子的长度为$n$，其中第$i$个词的词向量（word embedding）为$x_i\in\mathbb{R}^k$，$k$为维度大小。  
 
 首先，进行词向量的拼接操作：将每$h$个词拼接起来形成一个大小为$h$的词窗口，记为$x_{i:i+h-1}$，它表示词序列$x_{i},x_{i+1},\ldots,x_{i+h-1}$的拼接，其中，$i$表示词窗口中第一个词在整个句子中的位置，取值范围从$1$到$n-h+1$，$x_{i:i+h-1}\in\mathbb{R}^{hk}$。  
@@ -46,12 +53,16 @@ $$\hat c=max(c)$$
 最后，将所有卷积核得到的特征拼接起来即为文本的定长向量表示，对于文本分类问题，将其连接至softmax即构建出完整的模型。
 
 对于一般的短文本分类问题，上文所述的简单的文本卷积网络即可达到很高的正确率\[[1](#参考文献)\]。若想得到更抽象更高级的文本特征表示，可以构建深层文本卷积神经网络\[[2](#参考文献),[3](#参考文献)\]。
+
 ### 循环神经网络（RNN）
+
 循环神经网络是一种能对序列数据进行精确建模的有力工具。实际上，循环神经网络的理论计算能力是图灵完备的\[[4](#参考文献)\]。自然语言是一种典型的序列数据（词序列），近年来，循环神经网络及其变体（如long short term memory\[[5](#参考文献)\]等）在自然语言处理的多个领域，如语言模型、句法解析、语义角色标注（或一般的序列标注）、语义表示、图文生成、对话、机器翻译等任务上均表现优异甚至成为目前效果最好的方法。
+
 <p align="center">
 <img src="image/rnn.png" width = "60%" align="center"/><br/>
 图2. 循环神经网络按时间展开的示意图
 </p>
+
 循环神经网络按时间展开后如图2所示：在第$t$时刻，网络读入第$t$个输入$x_t$（向量表示）及前一时刻隐层的状态值$h_{t-1}$（向量表示，$h_0$一般初始化为$0$向量），计算得出本时刻隐层的状态值$h_t$，重复这一步骤直至读完所有输入。如果将循环神经网络所表示的函数记为$f$，则其公式可表示为：
 
 $$h_t=f(x_t,h_{t-1})=\sigma(W_{xh}x_t+W_{hh}h_{h-1}+b_h)$$
@@ -61,6 +72,7 @@ $$h_t=f(x_t,h_{t-1})=\sigma(W_{xh}x_t+W_{hh}h_{h-1}+b_h)$$
 在处理自然语言时，一般会先将词（one-hot表示）映射为其词向量（word embedding）表示，然后再作为循环神经网络每一时刻的输入$x_t$。此外，可以根据实际需要的不同在循环神经网络的隐层上连接其它层。如，可以把一个循环神经网络的隐层输出连接至下一个循环神经网络的输入构建深层（deep or stacked）循环神经网络，或者提取最后一个时刻的隐层状态作为句子表示进而使用分类模型等等。  
 
 ### 长短期记忆网络（LSTM）
+
 对于较长的序列数据，循环神经网络的训练过程中容易出现梯度消失或爆炸现象\[[6](#参考文献)\]。为了解决这一问题，Hochreiter S, Schmidhuber J. (1997)提出了LSTM(long short term memory\[[5](#参考文献)\])。  
 
 相比于简单的循环神经网络，LSTM增加了记忆单元$c$、输入门$i$、遗忘门$f$及输出门$o$。这些门及记忆单元组合起来大大提升了循环神经网络处理长序列数据的能力。若将基于LSTM的循环神经网络表示的函数记为$F$，则其公式为：
@@ -76,26 +88,33 @@ o_t & = \sigma(W_{xo}x_t+W_{ho}h_{h-1}+W_{co}c_{t}+b_o)\\\\
 h_t & = o_t\odot tanh(c_t)\\\\
 \end{align}
 其中，$i_t, f_t, c_t, o_t$分别表示输入门，遗忘门，记忆单元及输出门的向量值，带角标的$W$及$b$为模型参数，$tanh$为双曲正切函数，$\odot$表示逐元素（elementwise）的乘法操作。输入门控制着新输入进入记忆单元$c$的强度，遗忘门控制着记忆单元维持上一时刻值的强度，输出门控制着输出记忆单元的强度。三种门的计算方式类似，但有着完全不同的参数，它们各自以不同的方式控制着记忆单元$c$，如图3所示：
+
 <p align="center">
 <img src="image/lstm.png" width = "65%" align="center"/><br/>
 图3. 时刻$t$的LSTM [7]
 </p>
+
 LSTM通过给简单的循环神经网络增加记忆及控制门的方式，增强了其处理远距离依赖问题的能力。类似原理的改进还有Gated Recurrent Unit (GRU)\[[8](#参考文献)\]，其设计更为简洁一些。**这些改进虽然各有不同，但是它们的宏观描述却与简单的循环神经网络一样（如图2所示），即隐状态依据当前输入及前一时刻的隐状态来改变，不断地循环这一过程直至输入处理完毕：**
 
 $$ h_t=Recrurent(x_t,h_{t-1})$$
 
 其中，$Recrurent$可以表示简单的循环神经网络、GRU或LSTM。
+
 ### 栈式双向LSTM（Stacked Bidirectional LSTM）
+
 对于正常顺序的循环神经网络，$h_t$包含了$t$时刻之前的输入信息，也就是上文信息。同样，为了得到下文信息，我们可以使用反方向（将输入逆序处理）的循环神经网络。结合构建深层循环神经网络的方法（深层神经网络往往能得到更抽象和高级的特征表示），我们可以通过构建更加强有力的基于LSTM的栈式双向循环神经网络\[[9](#参考文献)\]，来对时序数据进行建模。  
 
 如图4所示（以三层为例），奇数层LSTM正向，偶数层LSTM反向，高一层的LSTM使用低一层LSTM及之前所有层的信息作为输入，对最高层LSTM序列使用时间维度上的最大池化即可得到文本的定长向量表示（这一表示充分融合了文本的上下文信息，并且对文本进行了深层次抽象），最后我们将文本表示连接至softmax构建分类模型。
+
 <p align="center">
 <img src="image/stacked_lstm.jpg" width=450><br/>
 图4. 栈式双向LSTM用于文本分类
 </p>
 
 ## 示例程序
+
 ### 数据集介绍
+
 我们以[IMDB情感分析数据集](http://ai.stanford.edu/%7Eamaas/data/sentiment/)为例进行介绍。IMDB数据集的训练集和测试集分别包含25000个已标注过的电影评论。其中，负面评论的得分小于等于4，正面评论的得分大于等于7，满分10分。
 ```text
 aclImdb
@@ -113,8 +132,11 @@ import sys
 import paddle.v2 as paddle
 ```
 ## 配置模型
+
 在该示例中，我们实现了两种文本分类算法，分别基于上文所述的[文本卷积神经网络](#文本卷积神经网络（CNN）)和[栈式双向LSTM](#栈式双向LSTM（Stacked Bidirectional LSTM）)。
+
 ### 文本卷积神经网络
+
 ```python
 def convolution_net(input_dim,
                     class_dim=2,
@@ -135,7 +157,9 @@ def convolution_net(input_dim,
     return cost
 ```
 网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API实现了卷积和池化操作。
+
 ### 栈式双向LSTM
+
 ```python
 def stacked_lstm_net(input_dim,
                      class_dim=2,
@@ -204,14 +228,18 @@ def stacked_lstm_net(input_dim,
     return cost
 ```
 网络的输入`stacked_num`表示的是LSTM的层数，需要是奇数，确保最高层LSTM正向。Paddle里面是通过一个fc和一个lstmemory来实现基于LSTM的循环神经网络。
+
 ## 训练模型
+
 ```python
 if __name__ == '__main__':
     # init
     paddle.init(use_gpu=False)
 ```
 启动paddle程序，use_gpu=False表示用CPU训练，如果系统支持GPU也可以修改成True使用GPU训练。
+
 ### 训练数据
+
 使用Paddle提供的数据集`dataset.imdb`中的API来读取训练数据。
 ```python
     print 'load dictionary...'
@@ -234,7 +262,9 @@ if __name__ == '__main__':
     feeding={'word': 0, 'label': 1}
 ```
 `feeding`用来指定`train_reader`和`test_reader`返回的数据与模型配置中data_layer的对应关系。这里表示reader返回的第0列数据对应`word`层，第1列数据对应`label`层。
+
 ### 构造模型
+
 ```python
     # Please choose the way to build the network
     # by uncommenting the corresponding line.
@@ -242,13 +272,17 @@ if __name__ == '__main__':
     # cost = stacked_lstm_net(dict_dim, class_dim=class_dim, stacked_num=3)
 ```
 该示例中默认使用`convolution_net`网络，如果使用`stacked_lstm_net`网络，注释相应的行即可。其中cost是网络的优化目标，同时cost包含了整个网络的拓扑信息。
+
 ### 网络参数
+
 ```python
     # create parameters
     parameters = paddle.parameters.create(cost)
 ```
 根据网络的拓扑构造网络参数。这里parameters是整个网络的参数集。
+
 ### 优化算法
+
 ```python
     # create optimizer
     adam_optimizer = paddle.optimizer.Adam(
@@ -257,7 +291,9 @@ if __name__ == '__main__':
         model_average=paddle.optimizer.ModelAverage(average_window=0.5))
 ```
 Paddle中提供了一系列优化算法的API，这里使用Adam优化算法。
+
 ### 训练
+
 可以通过`paddle.trainer.SGD`构造一个sgd trainer，并调用`trainer.train`来训练模型。
 ```python
     # End batch and end pass event handler
@@ -296,8 +332,11 @@ Test with Pass 0, {'classification_error_evaluator': 0.11432000249624252}
 ```
 
 ## 总结
+
 本章我们以情感分析为例，介绍了使用深度学习的方法进行端对端的短文本分类，并且使用PaddlePaddle完成了全部相关实验。同时，我们简要介绍了两种文本处理模型：卷积神经网络和循环神经网络。在后续的章节中我们会看到这两种基本的深度学习模型在其它任务上的应用。
+
 ## 参考文献
+
 1. Kim Y. [Convolutional neural networks for sentence classification](http://arxiv.org/pdf/1408.5882)[J]. arXiv preprint arXiv:1408.5882, 2014.
 2. Kalchbrenner N, Grefenstette E, Blunsom P. [A convolutional neural network for modelling sentences](http://arxiv.org/pdf/1404.2188.pdf?utm_medium=App.net&utm_source=PourOver)[J]. arXiv preprint arXiv:1404.2188, 2014.
 3. Yann N. Dauphin, et al. [Language Modeling with Gated Convolutional Networks](https://arxiv.org/pdf/1612.08083v1.pdf)[J] arXiv preprint arXiv:1612.08083, 2016.
diff --git a/05.understand_sentiment/index.en.html b/05.understand_sentiment/index.en.html
index 660c33fa8d75c782b8460983bfba2e9b861d7954..64d534154da6cee6a4ceb17986b00c2ac725f9e7 100644
--- a/05.understand_sentiment/index.en.html
+++ b/05.understand_sentiment/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -131,17 +131,17 @@ o_t & = \sigma(W_{xo}x_t+W_{ho}h_{h-1}+W_{co}c_{t}+b_o)\\\\
 h_t & = o_t\odot \tanh(c_t)\\\\
 \end{align}
 
-In the equation，$i_t, f_t, c_t, o_t$ stand for input gate, forget gate, memory cell and output gate, respectively. $W$ and $b$ are model parameters, $\tanh$ is a hyperbolic tangent, and $\odot$ denotes an element-wise product operation. The input gate controls the magnitude of the new input into the memory cell $c$; the forget gate controls the memory propagated from the last time step; the output gate controls the magnitutde of the output. The three gates are computed similarly with different parameters, and they influence memory cell $c$ separately, as shown in Figure 3:
+In the equation，$i_t, f_t, c_t, o_t$ stand for input gate, forget gate, memory cell and output gate, respectively. $W$ and $b$ are model parameters, $\tanh$ is a hyperbolic tangent, and $\odot$ denotes an element-wise product operation. The input gate controls the magnitude of the new input into the memory cell $c$; the forget gate controls the memory propagated from the last time step; the output gate controls the magnitude of the output. The three gates are computed similarly with different parameters, and they influence memory cell $c$ separately, as shown in Figure 3:
 
 <p align="center">
 <img src="image/lstm_en.png" width = "65%" align="center"/><br/>
 Figure 3. LSTM at time step $t$ [7].
 </p>
 
-LSTM enhances the ability of considering long-term reliance, with the help of memory cell and gate. Similar structures are also proposed in Gated Recurrent Unit (GRU)\[[8](Reference)\] with simpler design. **The structures are still similar to RNN, though with some modifications (As shown in Figure 2), i.e., latent status depends on input as well as the latent status of last time-step, and the process goes on recurrently until all input are consumed:**
+Similar to LSTM, other structures with memory cell and gates also enhance the network's long-term reliance. One such example is the **Gated Recurrent Unit**(GRU)\[[8](Reference)\. The structures are still similar to RNNs (as shown in Figure 2) in the following way: its latent status depends on both the current input as well as the latent status from the last time-step, and the process goes on recurrently until all the inputs are consumed:
 
-$$ h_t=Recrurent(x_t,h_{t-1})$$
-where $Recrurent$ is a simple RNN, GRU or LSTM.
+$$ h_t=Recurrent(x_t,h_{t-1})$$
+where $Recurrent$ is a simple RNN, GRU or LSTM.
 
 ### Stacked Bidirectional LSTM
 
diff --git a/05.understand_sentiment/index.html b/05.understand_sentiment/index.html
index 6340f3b509def6d132942b8d95a63c36d5caa718..b55e1f74d485f817516fd83a2a12eda85e2759a6 100644
--- a/05.understand_sentiment/index.html
+++ b/05.understand_sentiment/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,9 +42,10 @@
 <div id="markdown" style='display:none'>
 # 情感分析
 
-本教程源代码目录在[book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
+
 在自然语言处理中，情感分析一般是指判断一段文本所表达的情绪状态。其中，一段文本可以是一个句子，一个段落或一个文档。情绪状态可以是两类，如（正面，负面），（高兴，悲伤）；也可以是三类，如（积极，消极，中性）等等。情感分析的应用场景十分广泛，如把用户在购物网站（亚马逊、天猫、淘宝等）、旅游网站、电影评论网站上发表的评论分成正面评论和负面评论；或为了分析用户对于某一产品的整体使用感受，抓取产品的用户评论并进行情感分析等等。表格1展示了对电影评论进行情感分析的例子：
 
 | 电影评论       | 类别  |
@@ -61,16 +62,22 @@
 对于一段文本，BOW表示会忽略其词顺序、语法和句法，将这段文本仅仅看做是一个词集合，因此BOW方法并不能充分表示文本的语义信息。例如，句子“这部电影糟糕透了”和“一个乏味，空洞，没有内涵的作品”在情感分析中具有很高的语义相似度，但是它们的BOW表示的相似度为0。又如，句子“一个空洞，没有内涵的作品”和“一个不空洞而且有内涵的作品”的BOW相似度很高，但实际上它们的意思很不一样。  
 
 本章我们所要介绍的深度学习模型克服了BOW表示的上述缺陷，它在考虑词顺序的基础上把文本映射到低维度的语义空间，并且以端对端（end to end）的方式进行文本表示及分类，其性能相对于传统方法有显著的提升\[[1](#参考文献)\]。
+
 ## 模型概览
+
 本章所使用的文本表示模型为卷积神经网络（Convolutional Neural Networks）和循环神经网络(Recurrent Neural Networks)及其扩展。下面依次介绍这几个模型。
+
 ### 文本卷积神经网络（CNN）
+
 卷积神经网络经常用来处理具有类似网格拓扑结构（grid-like topology）的数据。例如，图像可以视为二维网格的像素点，自然语言可以视为一维的词序列。卷积神经网络可以提取多种局部特征，并对其进行组合抽象得到更高级的特征表示。实验表明，卷积神经网络能高效地对图像及文本问题进行建模处理。  
 
 卷积神经网络主要由卷积（convolution）和池化（pooling）操作构成，其应用及组合方式灵活多变，种类繁多。本小结我们以一种简单的文本分类卷积神经网络为例进行讲解\[[1](#参考文献)\]，如图1所示：
+
 <p align="center">
 <img src="image/text_cnn.png" width = "80%" align="center"/><br/>
 图1. 卷积神经网络文本分类模型
 </p>
+
 假设待处理句子的长度为$n$，其中第$i$个词的词向量（word embedding）为$x_i\in\mathbb{R}^k$，$k$为维度大小。  
 
 首先，进行词向量的拼接操作：将每$h$个词拼接起来形成一个大小为$h$的词窗口，记为$x_{i:i+h-1}$，它表示词序列$x_{i},x_{i+1},\ldots,x_{i+h-1}$的拼接，其中，$i$表示词窗口中第一个词在整个句子中的位置，取值范围从$1$到$n-h+1$，$x_{i:i+h-1}\in\mathbb{R}^{hk}$。  
@@ -88,12 +95,16 @@ $$\hat c=max(c)$$
 最后，将所有卷积核得到的特征拼接起来即为文本的定长向量表示，对于文本分类问题，将其连接至softmax即构建出完整的模型。
 
 对于一般的短文本分类问题，上文所述的简单的文本卷积网络即可达到很高的正确率\[[1](#参考文献)\]。若想得到更抽象更高级的文本特征表示，可以构建深层文本卷积神经网络\[[2](#参考文献),[3](#参考文献)\]。
+
 ### 循环神经网络（RNN）
+
 循环神经网络是一种能对序列数据进行精确建模的有力工具。实际上，循环神经网络的理论计算能力是图灵完备的\[[4](#参考文献)\]。自然语言是一种典型的序列数据（词序列），近年来，循环神经网络及其变体（如long short term memory\[[5](#参考文献)\]等）在自然语言处理的多个领域，如语言模型、句法解析、语义角色标注（或一般的序列标注）、语义表示、图文生成、对话、机器翻译等任务上均表现优异甚至成为目前效果最好的方法。
+
 <p align="center">
 <img src="image/rnn.png" width = "60%" align="center"/><br/>
 图2. 循环神经网络按时间展开的示意图
 </p>
+
 循环神经网络按时间展开后如图2所示：在第$t$时刻，网络读入第$t$个输入$x_t$（向量表示）及前一时刻隐层的状态值$h_{t-1}$（向量表示，$h_0$一般初始化为$0$向量），计算得出本时刻隐层的状态值$h_t$，重复这一步骤直至读完所有输入。如果将循环神经网络所表示的函数记为$f$，则其公式可表示为：
 
 $$h_t=f(x_t,h_{t-1})=\sigma(W_{xh}x_t+W_{hh}h_{h-1}+b_h)$$
@@ -103,6 +114,7 @@ $$h_t=f(x_t,h_{t-1})=\sigma(W_{xh}x_t+W_{hh}h_{h-1}+b_h)$$
 在处理自然语言时，一般会先将词（one-hot表示）映射为其词向量（word embedding）表示，然后再作为循环神经网络每一时刻的输入$x_t$。此外，可以根据实际需要的不同在循环神经网络的隐层上连接其它层。如，可以把一个循环神经网络的隐层输出连接至下一个循环神经网络的输入构建深层（deep or stacked）循环神经网络，或者提取最后一个时刻的隐层状态作为句子表示进而使用分类模型等等。  
 
 ### 长短期记忆网络（LSTM）
+
 对于较长的序列数据，循环神经网络的训练过程中容易出现梯度消失或爆炸现象\[[6](#参考文献)\]。为了解决这一问题，Hochreiter S, Schmidhuber J. (1997)提出了LSTM(long short term memory\[[5](#参考文献)\])。  
 
 相比于简单的循环神经网络，LSTM增加了记忆单元$c$、输入门$i$、遗忘门$f$及输出门$o$。这些门及记忆单元组合起来大大提升了循环神经网络处理长序列数据的能力。若将基于LSTM的循环神经网络表示的函数记为$F$，则其公式为：
@@ -118,26 +130,33 @@ o_t & = \sigma(W_{xo}x_t+W_{ho}h_{h-1}+W_{co}c_{t}+b_o)\\\\
 h_t & = o_t\odot tanh(c_t)\\\\
 \end{align}
 其中，$i_t, f_t, c_t, o_t$分别表示输入门，遗忘门，记忆单元及输出门的向量值，带角标的$W$及$b$为模型参数，$tanh$为双曲正切函数，$\odot$表示逐元素（elementwise）的乘法操作。输入门控制着新输入进入记忆单元$c$的强度，遗忘门控制着记忆单元维持上一时刻值的强度，输出门控制着输出记忆单元的强度。三种门的计算方式类似，但有着完全不同的参数，它们各自以不同的方式控制着记忆单元$c$，如图3所示：
+
 <p align="center">
 <img src="image/lstm.png" width = "65%" align="center"/><br/>
 图3. 时刻$t$的LSTM [7]
 </p>
+
 LSTM通过给简单的循环神经网络增加记忆及控制门的方式，增强了其处理远距离依赖问题的能力。类似原理的改进还有Gated Recurrent Unit (GRU)\[[8](#参考文献)\]，其设计更为简洁一些。**这些改进虽然各有不同，但是它们的宏观描述却与简单的循环神经网络一样（如图2所示），即隐状态依据当前输入及前一时刻的隐状态来改变，不断地循环这一过程直至输入处理完毕：**
 
 $$ h_t=Recrurent(x_t,h_{t-1})$$
 
 其中，$Recrurent$可以表示简单的循环神经网络、GRU或LSTM。
+
 ### 栈式双向LSTM（Stacked Bidirectional LSTM）
+
 对于正常顺序的循环神经网络，$h_t$包含了$t$时刻之前的输入信息，也就是上文信息。同样，为了得到下文信息，我们可以使用反方向（将输入逆序处理）的循环神经网络。结合构建深层循环神经网络的方法（深层神经网络往往能得到更抽象和高级的特征表示），我们可以通过构建更加强有力的基于LSTM的栈式双向循环神经网络\[[9](#参考文献)\]，来对时序数据进行建模。  
 
 如图4所示（以三层为例），奇数层LSTM正向，偶数层LSTM反向，高一层的LSTM使用低一层LSTM及之前所有层的信息作为输入，对最高层LSTM序列使用时间维度上的最大池化即可得到文本的定长向量表示（这一表示充分融合了文本的上下文信息，并且对文本进行了深层次抽象），最后我们将文本表示连接至softmax构建分类模型。
+
 <p align="center">
 <img src="image/stacked_lstm.jpg" width=450><br/>
 图4. 栈式双向LSTM用于文本分类
 </p>
 
 ## 示例程序
+
 ### 数据集介绍
+
 我们以[IMDB情感分析数据集](http://ai.stanford.edu/%7Eamaas/data/sentiment/)为例进行介绍。IMDB数据集的训练集和测试集分别包含25000个已标注过的电影评论。其中，负面评论的得分小于等于4，正面评论的得分大于等于7，满分10分。
 ```text
 aclImdb
@@ -155,8 +174,11 @@ import sys
 import paddle.v2 as paddle
 ```
 ## 配置模型
+
 在该示例中，我们实现了两种文本分类算法，分别基于上文所述的[文本卷积神经网络](#文本卷积神经网络（CNN）)和[栈式双向LSTM](#栈式双向LSTM（Stacked Bidirectional LSTM）)。
+
 ### 文本卷积神经网络
+
 ```python
 def convolution_net(input_dim,
                     class_dim=2,
@@ -177,7 +199,9 @@ def convolution_net(input_dim,
     return cost
 ```
 网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API实现了卷积和池化操作。
+
 ### 栈式双向LSTM
+
 ```python
 def stacked_lstm_net(input_dim,
                      class_dim=2,
@@ -246,14 +270,18 @@ def stacked_lstm_net(input_dim,
     return cost
 ```
 网络的输入`stacked_num`表示的是LSTM的层数，需要是奇数，确保最高层LSTM正向。Paddle里面是通过一个fc和一个lstmemory来实现基于LSTM的循环神经网络。
+
 ## 训练模型
+
 ```python
 if __name__ == '__main__':
     # init
     paddle.init(use_gpu=False)
 ```
 启动paddle程序，use_gpu=False表示用CPU训练，如果系统支持GPU也可以修改成True使用GPU训练。
+
 ### 训练数据
+
 使用Paddle提供的数据集`dataset.imdb`中的API来读取训练数据。
 ```python
     print 'load dictionary...'
@@ -276,7 +304,9 @@ if __name__ == '__main__':
     feeding={'word': 0, 'label': 1}
 ```
 `feeding`用来指定`train_reader`和`test_reader`返回的数据与模型配置中data_layer的对应关系。这里表示reader返回的第0列数据对应`word`层，第1列数据对应`label`层。
+
 ### 构造模型
+
 ```python
     # Please choose the way to build the network
     # by uncommenting the corresponding line.
@@ -284,13 +314,17 @@ if __name__ == '__main__':
     # cost = stacked_lstm_net(dict_dim, class_dim=class_dim, stacked_num=3)
 ```
 该示例中默认使用`convolution_net`网络，如果使用`stacked_lstm_net`网络，注释相应的行即可。其中cost是网络的优化目标，同时cost包含了整个网络的拓扑信息。
+
 ### 网络参数
+
 ```python
     # create parameters
     parameters = paddle.parameters.create(cost)
 ```
 根据网络的拓扑构造网络参数。这里parameters是整个网络的参数集。
+
 ### 优化算法
+
 ```python
     # create optimizer
     adam_optimizer = paddle.optimizer.Adam(
@@ -299,7 +333,9 @@ if __name__ == '__main__':
         model_average=paddle.optimizer.ModelAverage(average_window=0.5))
 ```
 Paddle中提供了一系列优化算法的API，这里使用Adam优化算法。
+
 ### 训练
+
 可以通过`paddle.trainer.SGD`构造一个sgd trainer，并调用`trainer.train`来训练模型。
 ```python
     # End batch and end pass event handler
@@ -338,8 +374,11 @@ Test with Pass 0, {'classification_error_evaluator': 0.11432000249624252}
 ```
 
 ## 总结
+
 本章我们以情感分析为例，介绍了使用深度学习的方法进行端对端的短文本分类，并且使用PaddlePaddle完成了全部相关实验。同时，我们简要介绍了两种文本处理模型：卷积神经网络和循环神经网络。在后续的章节中我们会看到这两种基本的深度学习模型在其它任务上的应用。
+
 ## 参考文献
+
 1. Kim Y. [Convolutional neural networks for sentence classification](http://arxiv.org/pdf/1408.5882)[J]. arXiv preprint arXiv:1408.5882, 2014.
 2. Kalchbrenner N, Grefenstette E, Blunsom P. [A convolutional neural network for modelling sentences](http://arxiv.org/pdf/1404.2188.pdf?utm_medium=App.net&utm_source=PourOver)[J]. arXiv preprint arXiv:1404.2188, 2014.
 3. Yann N. Dauphin, et al. [Language Modeling with Gated Convolutional Networks](https://arxiv.org/pdf/1612.08083v1.pdf)[J] arXiv preprint arXiv:1612.08083, 2016.
diff --git a/06.label_semantic_roles/README.en.md b/06.label_semantic_roles/README.en.md
index bf012416c45df0f839f5bb755a7561261a1b299d..f40269c3a3e93d59e425ceaad4985e2106651821 100644
--- a/06.label_semantic_roles/README.en.md
+++ b/06.label_semantic_roles/README.en.md
@@ -1,6 +1,6 @@
 # Semantic Role Labeling
 
-The source code of this chapter is live on [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
+The source code of this chapter is live on [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/06.label_semantic_roles).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
@@ -50,7 +50,7 @@ In this tutorial, our SRL system is built as an end-to-end system via a neural n
 
 ## Model
 
-**Recurrent Neural Networks** (*RNN*) are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike feed-forward neural networks, RNNs can model the dependencies between elements of sequences. As a variant of RNNs', LSTMs aim model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
+**Recurrent Neural Networks** (*RNN*) are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike feed-forward neural networks, RNNs can model the dependencies between elements of sequences. As a variant of RNNs', LSTMs aim model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
 
 ### Stacked Recurrent Neural Network
 
@@ -204,7 +204,7 @@ In addition to the data, we provide following resources:
 | predicate_dict | predicate dictionary, total 3162 predicates |
 | emb | a pre-trained word vector lookup table, 32-dimentional |
 
-We trained a language model on the English Wikipedia to get a word vector lookup table used to initialize the SRL model. While training the SRL model, the word vector lookup table is no longer updated. To learn more about the language model and the word vector lookup table, please refer to the tutorial [word vector](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md). There are 995,000,000 tokens in the training corpus, and the dictionary size is 4900,000 words. In the CoNLL 2005 training corpus, 5% of the words are not in the 4900,000 words, and we see them all as unknown words, represented by `<unk>`.
+We trained a language model on the English Wikipedia to get a word vector lookup table used to initialize the SRL model. While training the SRL model, the word vector lookup table is no longer updated. To learn more about the language model and the word vector lookup table, please refer to the tutorial [word vector](https://github.com/PaddlePaddle/book/blob/develop/04.word2vec/README.md). There are 995,000,000 tokens in the training corpus, and the dictionary size is 4900,000 words. In the CoNLL 2005 training corpus, 5% of the words are not in the 4900,000 words, and we see them all as unknown words, represented by `<unk>`.
 
 Here we fetch the dictionary, and print its size:
 
diff --git a/06.label_semantic_roles/README.md b/06.label_semantic_roles/README.md
index 309a166d5e598f7793032b2e0bf1dafefcd01854..fe92d852ad3e2a79e5be1d41aaef4ee26df182a1 100644
--- a/06.label_semantic_roles/README.md
+++ b/06.label_semantic_roles/README.md
@@ -1,6 +1,6 @@
 # 语义角色标注
 
-本教程源代码目录在[book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/06.label_semantic_roles)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
@@ -40,7 +40,7 @@ $$\mbox{[小明]}_{\mbox{Agent}}\mbox{[昨天]}_{\mbox{Time}}\mbox{[晚上]}_\mb
 
 ## 模型概览
 
-循环神经网络（Recurrent Neural Network）是一种对序列建模的重要模型，在自然语言处理任务中有着广泛地应用。不同于前馈神经网络（Feed-forward Neural Network），RNN能够处理输入之间前后关联的问题。LSTM是RNN的一种重要变种，常用来学习长序列中蕴含的长程依赖关系，我们在[情感分析](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment)一篇中已经介绍过，这一篇中我们依然利用LSTM来解决SRL问题。
+循环神经网络（Recurrent Neural Network）是一种对序列建模的重要模型，在自然语言处理任务中有着广泛地应用。不同于前馈神经网络（Feed-forward Neural Network），RNN能够处理输入之间前后关联的问题。LSTM是RNN的一种重要变种，常用来学习长序列中蕴含的长程依赖关系，我们在[情感分析](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment)一篇中已经介绍过，这一篇中我们依然利用LSTM来解决SRL问题。
 
 ### 栈式循环神经网络（Stacked Recurrent Neural Network）
 
@@ -182,7 +182,7 @@ conll05st-release/
 | predicate_dict | 谓词的词典，共计3162个词 |
 | emb | 一个训练好的词表，32维 |
 
-我们在英文维基百科上训练语言模型得到了一份词向量用来初始化SRL模型。在SRL模型训练过程中，词向量不再被更新。关于语言模型和词向量可以参考[词向量](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md) 这篇教程。我们训练语言模型的语料共有995,000,000个token，词典大小控制为4900,000词。CoNLL 2005训练语料中有5%的词不在这4900,000个词中，我们将它们全部看作未登录词，用`<unk>`表示。
+我们在英文维基百科上训练语言模型得到了一份词向量用来初始化SRL模型。在SRL模型训练过程中，词向量不再被更新。关于语言模型和词向量可以参考[词向量](https://github.com/PaddlePaddle/book/blob/develop/04.word2vec/README.md) 这篇教程。我们训练语言模型的语料共有995,000,000个token，词典大小控制为4900,000词。CoNLL 2005训练语料中有5%的词不在这4900,000个词中，我们将它们全部看作未登录词，用`<unk>`表示。
 
 获取词典，打印词典大小：
 
diff --git a/06.label_semantic_roles/index.en.html b/06.label_semantic_roles/index.en.html
index d2edc825c28fce2939e0ab99a06268de870770e5..74b6d477f0664222685f9a5de51fdb9dda9e8f79 100644
--- a/06.label_semantic_roles/index.en.html
+++ b/06.label_semantic_roles/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # Semantic Role Labeling
 
-The source code of this chapter is live on [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles).
+The source code of this chapter is live on [book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/06.label_semantic_roles).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
@@ -92,7 +92,7 @@ In this tutorial, our SRL system is built as an end-to-end system via a neural n
 
 ## Model
 
-**Recurrent Neural Networks** (*RNN*) are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike feed-forward neural networks, RNNs can model the dependencies between elements of sequences. As a variant of RNNs', LSTMs aim model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
+**Recurrent Neural Networks** (*RNN*) are important tools for sequence modeling and have been successfully used in some natural language processing tasks. Unlike feed-forward neural networks, RNNs can model the dependencies between elements of sequences. As a variant of RNNs', LSTMs aim model long-term dependency in long sequences. We have introduced this in [understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment). In this chapter, we continue to use LSTMs to solve SRL problems.
 
 ### Stacked Recurrent Neural Network
 
@@ -246,7 +246,7 @@ In addition to the data, we provide following resources:
 | predicate_dict | predicate dictionary, total 3162 predicates |
 | emb | a pre-trained word vector lookup table, 32-dimentional |
 
-We trained a language model on the English Wikipedia to get a word vector lookup table used to initialize the SRL model. While training the SRL model, the word vector lookup table is no longer updated. To learn more about the language model and the word vector lookup table, please refer to the tutorial [word vector](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md). There are 995,000,000 tokens in the training corpus, and the dictionary size is 4900,000 words. In the CoNLL 2005 training corpus, 5% of the words are not in the 4900,000 words, and we see them all as unknown words, represented by `<unk>`.
+We trained a language model on the English Wikipedia to get a word vector lookup table used to initialize the SRL model. While training the SRL model, the word vector lookup table is no longer updated. To learn more about the language model and the word vector lookup table, please refer to the tutorial [word vector](https://github.com/PaddlePaddle/book/blob/develop/04.word2vec/README.md). There are 995,000,000 tokens in the training corpus, and the dictionary size is 4900,000 words. In the CoNLL 2005 training corpus, 5% of the words are not in the 4900,000 words, and we see them all as unknown words, represented by `<unk>`.
 
 Here we fetch the dictionary, and print its size:
 
diff --git a/06.label_semantic_roles/index.html b/06.label_semantic_roles/index.html
index 3825f742c657c08c83adc446f0d6d5519ce78ede..4e7806580f7b1d83e50fd43b079ce6631c64da16 100644
--- a/06.label_semantic_roles/index.html
+++ b/06.label_semantic_roles/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # 语义角色标注
 
-本教程源代码目录在[book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/label_semantic_roles)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/label_semantic_roles](https://github.com/PaddlePaddle/book/tree/develop/06.label_semantic_roles)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
@@ -82,7 +82,7 @@ $$\mbox{[小明]}_{\mbox{Agent}}\mbox{[昨天]}_{\mbox{Time}}\mbox{[晚上]}_\mb
 
 ## 模型概览
 
-循环神经网络（Recurrent Neural Network）是一种对序列建模的重要模型，在自然语言处理任务中有着广泛地应用。不同于前馈神经网络（Feed-forward Neural Network），RNN能够处理输入之间前后关联的问题。LSTM是RNN的一种重要变种，常用来学习长序列中蕴含的长程依赖关系，我们在[情感分析](https://github.com/PaddlePaddle/book/tree/develop/understand_sentiment)一篇中已经介绍过，这一篇中我们依然利用LSTM来解决SRL问题。
+循环神经网络（Recurrent Neural Network）是一种对序列建模的重要模型，在自然语言处理任务中有着广泛地应用。不同于前馈神经网络（Feed-forward Neural Network），RNN能够处理输入之间前后关联的问题。LSTM是RNN的一种重要变种，常用来学习长序列中蕴含的长程依赖关系，我们在[情感分析](https://github.com/PaddlePaddle/book/tree/develop/05.understand_sentiment)一篇中已经介绍过，这一篇中我们依然利用LSTM来解决SRL问题。
 
 ### 栈式循环神经网络（Stacked Recurrent Neural Network）
 
@@ -224,7 +224,7 @@ conll05st-release/
 | predicate_dict | 谓词的词典，共计3162个词 |
 | emb | 一个训练好的词表，32维 |
 
-我们在英文维基百科上训练语言模型得到了一份词向量用来初始化SRL模型。在SRL模型训练过程中，词向量不再被更新。关于语言模型和词向量可以参考[词向量](https://github.com/PaddlePaddle/book/blob/develop/word2vec/README.md) 这篇教程。我们训练语言模型的语料共有995,000,000个token，词典大小控制为4900,000词。CoNLL 2005训练语料中有5%的词不在这4900,000个词中，我们将它们全部看作未登录词，用`<unk>`表示。
+我们在英文维基百科上训练语言模型得到了一份词向量用来初始化SRL模型。在SRL模型训练过程中，词向量不再被更新。关于语言模型和词向量可以参考[词向量](https://github.com/PaddlePaddle/book/blob/develop/04.word2vec/README.md) 这篇教程。我们训练语言模型的语料共有995,000,000个token，词典大小控制为4900,000词。CoNLL 2005训练语料中有5%的词不在这4900,000个词中，我们将它们全部看作未登录词，用`<unk>`表示。
 
 获取词典，打印词典大小：
 
diff --git a/07.machine_translation/README.en.md b/07.machine_translation/README.en.md
index 5133b8643589d334a1c368d058a8ef1cfcc2dd6c..e306d218552543f00c25cfb9a4965ae5993e5812 100644
--- a/07.machine_translation/README.en.md
+++ b/07.machine_translation/README.en.md
@@ -1,6 +1,6 @@
 # Machine Translation
 
-The source codes is located at [book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/machine_translation). Please refer to the PaddlePaddle [installation tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) if you are a first time user.
+The source codes is located at [book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/07.machine_translation). Please refer to the PaddlePaddle [installation tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) if you are a first time user.
 
 ## Background
 
diff --git a/07.machine_translation/README.md b/07.machine_translation/README.md
index fcc703b7b5a9f379a2c446b231d743a0a5d5c21c..658c1e0506c0c041a8e38d00a74721665177e352 100644
--- a/07.machine_translation/README.md
+++ b/07.machine_translation/README.md
@@ -1,6 +1,6 @@
 # 机器翻译
 
-本教程源代码目录在[book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/machine_translation)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/07.machine_translation)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/07.machine_translation/index.en.html b/07.machine_translation/index.en.html
index 944bf7251e84b7b93c705b3e6dad3ea1478c302c..1df7352b7fc8a1fcb3e83e846843baedfeda77ca 100644
--- a/07.machine_translation/index.en.html
+++ b/07.machine_translation/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # Machine Translation
 
-The source codes is located at [book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/machine_translation). Please refer to the PaddlePaddle [installation tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) if you are a first time user.
+The source codes is located at [book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/07.machine_translation). Please refer to the PaddlePaddle [installation tutorial](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst) if you are a first time user.
 
 ## Background
 
diff --git a/07.machine_translation/index.html b/07.machine_translation/index.html
index 77cbc6fca36f8ce423c018bad453fd12cdf45bb2..b73212c4911e7d80efa1b107fda3aaa7297671ac 100644
--- a/07.machine_translation/index.html
+++ b/07.machine_translation/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # 机器翻译
 
-本教程源代码目录在[book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/machine_translation)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/machine_translation](https://github.com/PaddlePaddle/book/tree/develop/07.machine_translation)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/07.machine_translation/api_train.py b/07.machine_translation/train.py
similarity index 100%
rename from 07.machine_translation/api_train.py
rename to 07.machine_translation/train.py
diff --git a/08.recommender_system/README.en.md b/08.recommender_system/README.en.md
index 881fdaee25dac6dbf0874db2551757b025ef2f1d..75bed8af0665a202ce0cfcb165dc8305f42e1722 100644
--- a/08.recommender_system/README.en.md
+++ b/08.recommender_system/README.en.md
@@ -1,6 +1,6 @@
 # Personalized Recommendation
 
-The source code of this tutorial is in [book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/recommender_system).
+The source code of this tutorial is in [book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/08.recommender_system).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
diff --git a/08.recommender_system/README.md b/08.recommender_system/README.md
index 94f072db7233681c53408e44a57dc93483c1cfe7..812042ef9e12304a08ec112e4f4ffbd32da161c3 100644
--- a/08.recommender_system/README.md
+++ b/08.recommender_system/README.md
@@ -1,6 +1,6 @@
 # 个性化推荐
 
-本教程源代码目录在[book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/recommender_system)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/08.recommender_system)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/08.recommender_system/index.en.html b/08.recommender_system/index.en.html
index 922d87f6fd477d5e32284e05162dba1f9ce0e7c6..07ebae273e2282f01779d8ac1e49a0495510ffad 100644
--- a/08.recommender_system/index.en.html
+++ b/08.recommender_system/index.en.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # Personalized Recommendation
 
-The source code of this tutorial is in [book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/recommender_system).
+The source code of this tutorial is in [book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/08.recommender_system).
 
 For instructions on getting started with PaddlePaddle, see [PaddlePaddle installation guide](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_en.rst).
 
diff --git a/08.recommender_system/index.html b/08.recommender_system/index.html
index 491b1a6d52e4efa01838cb39531b6f01dd88349a..26514f81b6b97a13259e70083463372e9fbab8c9 100644
--- a/08.recommender_system/index.html
+++ b/08.recommender_system/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
@@ -42,7 +42,7 @@
 <div id="markdown" style='display:none'>
 # 个性化推荐
 
-本教程源代码目录在[book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/recommender_system)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
+本教程源代码目录在[book/recommender_system](https://github.com/PaddlePaddle/book/tree/develop/08.recommender_system)， 初次使用请参考PaddlePaddle[安装教程](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。
 
 ## 背景介绍
 
diff --git a/README.md b/README.md
index 68ffae7e8ec50b11b7ee7c5a9a31215a2ca38544..94b98c6287b44c5c42b889fed5e3d45aa7372e7a 100644
--- a/README.md
+++ b/README.md
@@ -16,17 +16,9 @@
 
 ## 运行这本书
 
-您现在在看的这本书是一本“交互式”电子书 —— 每一章都可以运行在一个
-Jupyter Notebook 里。
-
-我们把 Jupyter、PaddlePaddle、以及各种被依赖的软件都打包进一个 Docker
-image 了。所以您不需要自己来安装各种软件，只需要安装 Docker 即可。如果
-您使用 Windows，可以参
-考[这里](https://www.docker.com/docker-windows)。如果您使用 Mac，可以
-参考[这里](https://www.docker.com/docker-mac)。 对于各种 Linux 发行版，
-请参考https://www.docker.com 。如果您使用 Windows 或者 Mac，可以通过如
-下方法给 Docker 更多内存和CPU资源
-(http://stackoverflow.com/a/39720010/724872)。
+您现在在看的这本书是一本“交互式”电子书 —— 每一章都可以运行在一个Jupyter Notebook里。
+
+我们把Jupyter、PaddlePaddle、以及各种被依赖的软件都打包进一个Docker image了。所以您不需要自己来安装各种软件，只需要安装Docker即可。对于各种Linux发行版，请参考 https://www.docker.com 。如果您使用[Windows](https://www.docker.com/docker-windows)或者[Mac](https://www.docker.com/docker-mac)，可以考虑[给Docker更多内存和CPU资源](http://stackoverflow.com/a/39720010/724872)。
 
 只需要在命令行窗口里运行：
 
@@ -34,11 +26,9 @@ image 了。所以您不需要自己来安装各种软件，只需要安装 Dock
 docker run -d -p 8888:8888 paddlepaddle/book
 ```
 
-这个命令会从 DockerHub.com 下载本书的 Docker image 并且运行之。请在浏
-览器里访问 http://localhost:8888 即可阅读和在线编辑本书。
+会从DockerHub.com下载和运行本书的Docker image。阅读和在线编辑本书请在浏览器里访问 http://localhost:8888 。
 
-如果您访问 DockerHub.com 很慢，可以试试我们的另一个镜像
-docker.paddlepaddle.org：
+如果您访问DockerHub.com很慢，可以试试我们的另一个镜像docker.paddlepaddle.org：
 
 ```bash
 docker run -d -p 8888:8888 docker.paddlepaddle.org/book
@@ -46,14 +36,9 @@ docker run -d -p 8888:8888 docker.paddlepaddle.org/book
 
 ## 贡献内容
 
-您要是能贡献新的章节那就太好了！请发 Pull Requests 把您写的章节加入到
-`/pending` 下面的一个子目录里。当这一章稳定下来，我们一起把您的目录挪
-到根目录。
-
-为了写作、运行、调试，您需要安装 Python 2.x, Go >1.5. 你可以用这
-个[脚本程序](https://github.com/PaddlePaddle/book/blob/develop/.tools/convert-markdown-into-ipynb-and-test.sh)来
-生成 Docker image。
+您要是能贡献新的章节那就太好了！请发Pull Requests把您写的章节加入到`/pending`下面的一个子目录里。当这一章稳定下来，我们一起把您的目录挪到根目录。
 
+为了写作、运行、调试，您需要安装Python 2.x和Go >1.5, 并可以用[脚本程序](https://github.com/PaddlePaddle/book/blob/develop/.tools/convert-markdown-into-ipynb-and-test.sh)来生成新的Docker image。
 
 **Note:** We also provide [English Readme](https://github.com/PaddlePaddle/book/blob/develop/README.en.md) for PaddlePaddle book.
 
diff --git a/index.en.html b/index.en.html
index cbfb7757cee223d335a67ec368ec03a2ea3d1f55..f7ae7db3188cb4dd4a28a424c62d9603e8dc0f32 100644
--- a/index.en.html
+++ b/index.en.html
@@ -11,6 +11,7 @@
 * {
     font-family:"Roboto","Lato","proxima-nova","Helvetica Neue",Arial,sans-serif;
 }
+
 .left-panel {
     background: #E5E6EA;
 }
@@ -64,7 +65,7 @@
 <body>
     <nav class="navbar navbar-toggleable-md navbar-inverse bg-inverse">
         <a class="navbar-brand mr-auto" href="#">
-            <img alt="PaddlePaddle" src="./.theme/PP_w.png">
+            <img alt="PaddlePaddle" src="./.tools/theme/PP_w.png">
         </a>
         <ul class="nav navbar-nav">
           <li class="nav-item">
diff --git a/index.html b/index.html
index 9cc744529ec35fe5dcb356bd1fcb3a2bd354762c..e4bb6268c925a9b527698d2818c446c9814b8b7e 100644
--- a/index.html
+++ b/index.html
@@ -11,6 +11,7 @@
 * {
     font-family:"Roboto","Lato","proxima-nova","Helvetica Neue",Arial,sans-serif;
 }
+
 .left-panel {
     background: #E5E6EA;
 }
@@ -68,7 +69,7 @@
 <body>
     <nav class="navbar navbar-toggleable-md navbar-inverse bg-inverse">
         <a class="navbar-brand mr-auto" href="#">
-            <img alt="PaddlePaddle" src="./.theme/PP_w.png">
+            <img alt="PaddlePaddle" src="./.tools/theme/PP_w.png">
         </a>
         <ul class="nav navbar-nav">
           <li class="nav-item">
diff --git a/pending/gan/index.html b/pending/gan/index.html
index b2d90bde37681294f74d1ac8a051e630c463c838..fb4009c11912a394a88ceafb60c821818a08a109 100644
--- a/pending/gan/index.html
+++ b/pending/gan/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/image_caption/index.html b/pending/image_caption/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/image_caption/index.html
+++ b/pending/image_caption/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/image_detection/index.html b/pending/image_detection/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/image_detection/index.html
+++ b/pending/image_detection/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/image_qa/index.html b/pending/image_qa/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/image_qa/index.html
+++ b/pending/image_qa/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/query_relationship/index.html b/pending/query_relationship/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/query_relationship/index.html
+++ b/pending/query_relationship/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/skip_thought/index.html b/pending/skip_thought/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/skip_thought/index.html
+++ b/pending/skip_thought/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
diff --git a/pending/speech_recognition/index.html b/pending/speech_recognition/index.html
index 1cce2a25ce4ffbbabca7791673b824fbfa8e95a3..efbfd8a4e368928d761789c0a475c863ab586e34 100644
--- a/pending/speech_recognition/index.html
+++ b/pending/speech_recognition/index.html
@@ -14,13 +14,13 @@
   });
   </script>
   <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js" async></script>
-  <script type="text/javascript" src="../.tmpl/marked.js">
+  <script type="text/javascript" src="../.tools/theme/marked.js">
   </script>
   <link href="http://cdn.bootcss.com/highlight.js/9.9.0/styles/darcula.min.css" rel="stylesheet">
   <script src="http://cdn.bootcss.com/highlight.js/9.9.0/highlight.min.js"></script>
   <link href="http://cdn.bootcss.com/bootstrap/4.0.0-alpha.6/css/bootstrap.min.css" rel="stylesheet">
   <link href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" rel="stylesheet">
-  <link href="../.tmpl/github-markdown.css" rel='stylesheet'>
+  <link href="../.tools/theme/github-markdown.css" rel='stylesheet'>
 </head>
 <style type="text/css" >
 .markdown-body {
