Merge branch 'develop' of https://github.com/PaddlePaddle/book into little-fix-in-mnist

.dockerignore

+Dockerfile

.gitignore

@@ -4,3 +4,5 @@ pandoc.template
 .DS_Store
 .idea
 py_env*
+*.ipynb
+build

.pre-commit-config.yaml

@@ -34,7 +34,7 @@
     -   id: convert-markdown-into-html
         name: convert-markdown-into-html
         description: Convert README.md into index.html and README.en.md into index.en.html
-        entry: python pre-commit-hooks/convert_markdown_into_html.py
+        entry: python .pre-commit-hooks/convert_markdown_into_html.py
         language: system
         files: .+README(\.en)?\.md$
 

.tools/build_docker.sh

+#!/bin/bash
+cur_path="$(cd "$(dirname "$0")" && pwd -P)"
+cd $cur_path/../
+
+#convert md to ipynb
+.tools/convert-markdown-into-ipynb-and-test.sh
+
+paddle_tag=0.10.0rc2
+book_tag=latest
+
+#generate docker file
+if [ ${USE_UBUNTU_REPO_MIRROR} ]; then
+  update_mirror_cmd="sed 's@http:\/\/archive.ubuntu.com\/ubuntu\/@mirror:\/\/mirrors.ubuntu.com\/mirrors.txt@' -i /etc/apt/sources.list && \\"
+else
+  update_mirror_cmd="\\"
+fi
+
+#build docker image
+echo "paddle_tag:"$paddle_tag
+echo "book_tag:"$book_tag
+
+cat > Dockerfile <<EOF
+FROM paddlepaddle/paddle:${paddle_tag}
+MAINTAINER PaddlePaddle Authors <paddle-dev@baidu.com>
+
+COPY . /book
+
+RUN pip install -U nltk \
+    && python /book/.tools/cache_dataset.py
+
+RUN ${update_mirror_cmd}
+    apt-get update && \
+    apt-get install -y locales && \
+    apt-get -y install gcc && \
+    apt-get -y clean && \
+    localedef -f UTF-8 -i en_US en_US.UTF-8 && \
+    pip install -U matplotlib jupyter numpy requests scipy
+
+EXPOSE 8888
+CMD ["sh", "-c", "jupyter notebook --ip=0.0.0.0 --no-browser --NotebookApp.token='' --NotebookApp.disable_check_xsrf=True /book/"]
+EOF
+
+docker build --no-cache  -t paddlepaddle/book:${paddle_tag}  -t paddlepaddle/book:${book_tag} .

.tools/cache_dataset.py

+#!/bin/env python
+import paddle.v2.dataset as dataset
+import nltk
+
+#cifar
+dataset.common.download(dataset.cifar.CIFAR100_URL, 'cifar',
+                        dataset.cifar.CIFAR100_MD5)
+dataset.common.download(dataset.cifar.CIFAR10_URL, 'cifar',
+                        dataset.cifar.CIFAR10_MD5)
+
+# Cache conll05
+dataset.common.download(dataset.conll05.WORDDICT_URL, 'conll05st', \
+                        dataset.conll05.WORDDICT_MD5)
+dataset.common.download(dataset.conll05.VERBDICT_URL, 'conll05st', \
+                        dataset.conll05.VERBDICT_MD5)
+dataset.common.download(dataset.conll05.TRGDICT_URL, 'conll05st', \
+                        dataset.conll05.TRGDICT_MD5)
+dataset.common.download(dataset.conll05.EMB_URL, 'conll05st',
+                        dataset.conll05.EMB_MD5)
+dataset.common.download(dataset.conll05.DATA_URL, 'conll05st',
+                        dataset.conll05.DATA_MD5)
+
+# Cache imdb
+dataset.common.download(dataset.imdb.URL, "imdb", dataset.imdb.MD5)
+
+# Cache imikolov
+dataset.common.download(dataset.imikolov.URL, "imikolov", dataset.imikolov.MD5)
+
+# Cache movielens
+dataset.common.download('http://files.grouplens.org/datasets/movielens/ml-1m.zip',\
+                        'movielens','c4d9eecfca2ab87c1945afe126590906')
+
+# Cache nltk
+nltk.download('movie_reviews', download_dir=dataset.common.DATA_HOME)
+
+# Cache uci housing
+dataset.common.download(dataset.uci_housing.URL, "uci_housing", \
+                        dataset.uci_housing.MD5)
+
+# Cache vmt14
+dataset.common.download(dataset.wmt14.URL_TRAIN, "wmt14",\
+                        dataset.wmt14.MD5_TRAIN)
+
+#mnist
+dataset.common.download(dataset.mnist.TRAIN_IMAGE_URL, 'mnist',
+                        dataset.mnist.TRAIN_IMAGE_MD5)
+dataset.common.download(dataset.mnist.TRAIN_LABEL_URL, 'mnist',
+                        dataset.mnist.TRAIN_LABEL_MD5)
+dataset.common.download(dataset.mnist.TEST_IMAGE_URL, 'mnist',
+                        dataset.mnist.TEST_IMAGE_MD5)
+dataset.common.download(dataset.mnist.TEST_LABEL_URL, 'mnist',
+                        dataset.mnist.TEST_LABEL_MD5)

tools/convert-markdown-into-ipynb-and-test.sh → .tools/convert-markdown-into-ipynb-and-test.sh

@@ -5,14 +5,14 @@ if [ $? -ne 0 ]; then
     exit 1
 fi
 
-GOPATH=/tmp/go go get -u github.com/wangkuiyi/ipynb/markdown-to-ipynb
+export GOPATH=~/go; go get -u github.com/wangkuiyi/ipynb/markdown-to-ipynb
 
-cur_path=$(dirname $(readlink -f $0))
+cur_path="$(cd "$(dirname "$0")" && pwd -P)"
 cd $cur_path/../
 
 #convert md to ipynb
 for file in */{README,README\.en}.md ; do
-    /tmp/go/bin/markdown-to-ipynb < $file > ${file%.*}".ipynb"
+    ~/go/bin/markdown-to-ipynb < $file > ${file%.*}".ipynb"
     if [ $? -ne 0 ]; then
         echo >&2 "markdown-to-ipynb $file error"
         exit 1

.travis.yml

@@ -19,7 +19,7 @@ before_install:
   -  pip install -U virtualenv pre-commit pip
   -  GOPATH=/tmp/go go get -u github.com/wangkuiyi/ipynb/markdown-to-ipynb
 script:
-  -  PATH=/tmp/go/bin:$PATH travis/precommit.sh
+  -  PATH=/tmp/go/bin:$PATH .travis/precommit.sh
 notifications:
   email:
     on_success: change

fit_a_line/README.en.ipynb → 01.fit_a_line/README.en.ipynb

@@ -189,7 +189,7 @@
         "                                size=1,\n",
         "                                act=paddle.activation.Linear())\n",
         "y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))\n",
-        "cost = paddle.layer.regression_cost(input=y_predict, label=y)\n"
+        "cost = paddle.layer.mse_cost(input=y_predict, label=y)\n"
       ],
       "outputs": [
         {

fit_a_line/README.en.md → 01.fit_a_line/README.en.md

@@ -132,7 +132,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### Create Parameters
 

fit_a_line/README.ipynb → 01.fit_a_line/README.ipynb

@@ -183,7 +183,7 @@
         "                                size=1,\n",
         "                                act=paddle.activation.Linear())\n",
         "y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))\n",
-        "cost = paddle.layer.regression_cost(input=y_predict, label=y)\n"
+        "cost = paddle.layer.mse_cost(input=y_predict, label=y)\n"
       ],
       "outputs": [
         {

fit_a_line/README.md → 01.fit_a_line/README.md

@@ -126,7 +126,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### 创建参数
 

fit_a_line/index.en.html → 01.fit_a_line/index.en.html

@@ -174,7 +174,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### Create Parameters
 

fit_a_line/index.html → 01.fit_a_line/index.html

@@ -168,7 +168,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### 创建参数
 

fit_a_line/train.py → 01.fit_a_line/train.py

@@ -10,7 +10,7 @@ def main():
     x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
     y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear())
     y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-    cost = paddle.layer.regression_cost(input=y_predict, label=y)
+    cost = paddle.layer.mse_cost(input=y_predict, label=y)
 
     # create parameters
     parameters = paddle.parameters.create(cost)

image_classification/README.en.md → 03.image_classification/README.en.md

@@ -148,9 +148,9 @@ Figure 10. ResNet model for ImageNet
 
 ## Dataset
 
-Commonly used public datasets for image classification are CIFAR(https://www.cs.toronto.edu/~kriz/cifar.html), ImageNet(http://image-net.org/), COCO(http://mscoco.org/), etc. Those used for fine-grained image classification are CUB-200-2011(http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), Stanford Dog(http://vision.stanford.edu/aditya86/ImageNetDogs/), Oxford-flowers(http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
+Commonly used public datasets for image classification are [CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html), [ImageNet](http://image-net.org/), [COCO](http://mscoco.org/), etc. Those used for fine-grained image classification are [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), [Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/), [Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
 
-Since ImageNet is too large to be downloaded and trained efficiently, we use CIFAR-10 (https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
+Since ImageNet is too large to be downloaded and trained efficiently, we use [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
 
 <p align="center">
 <img src="image/cifar.png" width="350"><br/>
@@ -185,7 +185,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
 
 1. Define input data and its dimension
 
-        The input to the network is defined as `paddle.layer.data`, or image pixels in the context of image classification. The images in CIFAR10 are 32x32 color images of three channels. Therefore, the size of the input data is 3072 (3x32x32), and the number of categories is 10.
+    The input to the network is defined as `paddle.layer.data`, or image pixels in the context of image classification. The images in CIFAR10 are 32x32 color images of three channels. Therefore, the size of the input data is 3072 (3x32x32), and the number of categories is 10.
 
     ```python
     datadim = 3 * 32 * 32
@@ -199,7 +199,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
     ```python
     net = vgg_bn_drop(image)
     ```
-        The input to VGG main module is from the data layer. `vgg_bn_drop` defines a 16-layer VGG network, with each convolutional layer followed by BN and dropout layers. Here is the definition in detail:
+    The input to VGG main module is from the data layer. `vgg_bn_drop` defines a 16-layer VGG network, with each convolutional layer followed by BN and dropout layers. Here is the definition in detail:
 
     ```python
     def vgg_bn_drop(input):
@@ -232,17 +232,15 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
         return fc2
     ```
 
-        2.1. First, define a convolution block or conv_block. The default convolution kernel is 3x3, and the default pooling size is 2x2 with stride 2. Dropout specifies the probability in dropout operation. Function `img_conv_group` is defined in `paddle.networks` consisting of a series of `Conv->BN->ReLu->Dropout` and a `Pooling`.
+    2.1. First, define a convolution block or conv_block. The default convolution kernel is 3x3, and the default pooling size is 2x2 with stride 2. Dropout specifies the probability in dropout operation. Function `img_conv_group` is defined in `paddle.networks` consisting of a series of `Conv->BN->ReLu->Dropout` and a `Pooling`.
 
+    2.2. Five groups of convolutions. The first two groups perform two convolutions, while the last three groups perform three convolutions. The dropout rate of the last convolution in each group is set to 0, which means there is no dropout for this layer.
 
-        2.2. Five groups of convolutions. The first two groups perform two convolutions, while the last three groups perform three convolutions. The dropout rate of the last convolution in each group is set to 0, which means there is no dropout for this layer.
-
-
-        2.3. The last two layers are fully-connected layers of dimension 512.
+    2.3. The last two layers are fully-connected layers of dimension 512.
 
 3. Define Classifier
 
-        The above VGG network extracts high-level features and maps them to a vector of the same size as the categories. Softmax function or classifier is then used for calculating the probability of the image belonging to each category.
+    The above VGG network extracts high-level features and maps them to a vector of the same size as the categories. Softmax function or classifier is then used for calculating the probability of the image belonging to each category.
 
     ```python
     out = paddle.layer.fc(input=net,
@@ -252,7 +250,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
 
 4. Define Loss Function and Outputs
 
-        In the context of supervised learning, labels of training images are defined in `paddle.layer.data` as well. During training, the cross-entropy loss function is used and the loss is the output of the network. During testing, the outputs are the probabilities calculated in the classifier.
+    In the context of supervised learning, labels of training images are defined in `paddle.layer.data` as well. During training, the cross-entropy loss function is used and the loss is the output of the network. During testing, the outputs are the probabilities calculated in the classifier.
 
     ```python
     lbl = paddle.layer.data(

image_classification/README.md → 03.image_classification/README.md

@@ -135,7 +135,7 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
 
 ## 数据准备
 
-通用图像分类公开的标准数据集常用的有[CIFAR](<https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
+通用图像分类公开的标准数据集常用的有[CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
 
 由于ImageNet数据集较大，下载和训练较慢，为了方便大家学习，我们使用[CIFAR10](<https://www.cs.toronto.edu/~kriz/cifar.html>)数据集。CIFAR10数据集包含60,000张32x32的彩色图片，10个类别，每个类包含6,000张。其中50,000张图片作为训练集，10000张作为测试集。图11从每个类别中随机抽取了10张图片，展示了所有的类别。
 
@@ -220,7 +220,7 @@ paddle.init(use_gpu=False, trainer_count=1)
         return fc2
     ```
 
-    2.1. 首先定义了一组卷积网络，即conv_block。卷积核大小为3x3，池化窗口大小为2x2，窗口滑动大小为2，groups决定每组VGG模块是几次连续的卷积操作，dropouts指定Dropout操作的概率。所使用的`img_conv_group`是在`paddle.networks`中预定义的模块，由若干组 `Conv->BN->ReLu->Dropout` 和 一组 `Pooling` 组成，
+    2.1. 首先定义了一组卷积网络，即conv_block。卷积核大小为3x3，池化窗口大小为2x2，窗口滑动大小为2，groups决定每组VGG模块是几次连续的卷积操作，dropouts指定Dropout操作的概率。所使用的`img_conv_group`是在`paddle.networks`中预定义的模块，由若干组 Conv->BN->ReLu->Dropout 和 一组 Pooling 组成。
 
     2.2. 五组卷积操作，即 5个conv_block。 第一、二组采用两次连续的卷积操作。第三、四、五组采用三次连续的卷积操作。每组最后一个卷积后面Dropout概率为0，即不使用Dropout操作。
 

image_classification/index.en.html → 03.image_classification/index.en.html

@@ -190,9 +190,9 @@ Figure 10. ResNet model for ImageNet
 
 ## Dataset
 
-Commonly used public datasets for image classification are CIFAR(https://www.cs.toronto.edu/~kriz/cifar.html), ImageNet(http://image-net.org/), COCO(http://mscoco.org/), etc. Those used for fine-grained image classification are CUB-200-2011(http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), Stanford Dog(http://vision.stanford.edu/aditya86/ImageNetDogs/), Oxford-flowers(http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
+Commonly used public datasets for image classification are [CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html), [ImageNet](http://image-net.org/), [COCO](http://mscoco.org/), etc. Those used for fine-grained image classification are [CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html), [Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/), [Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/), etc. Among these, the ImageNet dataset is the largest. Most research results are reported on ImageNet as mentioned in the Model Overview section. Since 2010, the ImageNet dataset has gone through some changes. The commonly used ImageNet-2012 dataset contains 1000 categories. There are 1,281,167 training images, ranging from 732 to 1200 images per category, and 50,000 validation images with 50 images per category in average.
 
-Since ImageNet is too large to be downloaded and trained efficiently, we use CIFAR-10 (https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
+Since ImageNet is too large to be downloaded and trained efficiently, we use [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) in this tutorial. The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Figure 11 shows all the classes in CIFAR-10 as well as 10 images randomly sampled from each category.
 
 <p align="center">
 <img src="image/cifar.png" width="350"><br/>
@@ -227,7 +227,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
 
 1. Define input data and its dimension
 
-        The input to the network is defined as `paddle.layer.data`, or image pixels in the context of image classification. The images in CIFAR10 are 32x32 color images of three channels. Therefore, the size of the input data is 3072 (3x32x32), and the number of categories is 10.
+    The input to the network is defined as `paddle.layer.data`, or image pixels in the context of image classification. The images in CIFAR10 are 32x32 color images of three channels. Therefore, the size of the input data is 3072 (3x32x32), and the number of categories is 10.
 
     ```python
     datadim = 3 * 32 * 32
@@ -241,7 +241,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
     ```python
     net = vgg_bn_drop(image)
     ```
-        The input to VGG main module is from the data layer. `vgg_bn_drop` defines a 16-layer VGG network, with each convolutional layer followed by BN and dropout layers. Here is the definition in detail:
+    The input to VGG main module is from the data layer. `vgg_bn_drop` defines a 16-layer VGG network, with each convolutional layer followed by BN and dropout layers. Here is the definition in detail:
 
     ```python
     def vgg_bn_drop(input):
@@ -274,17 +274,15 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
         return fc2
     ```
 
-        2.1. First, define a convolution block or conv_block. The default convolution kernel is 3x3, and the default pooling size is 2x2 with stride 2. Dropout specifies the probability in dropout operation. Function `img_conv_group` is defined in `paddle.networks` consisting of a series of `Conv->BN->ReLu->Dropout` and a `Pooling`.
+    2.1. First, define a convolution block or conv_block. The default convolution kernel is 3x3, and the default pooling size is 2x2 with stride 2. Dropout specifies the probability in dropout operation. Function `img_conv_group` is defined in `paddle.networks` consisting of a series of `Conv->BN->ReLu->Dropout` and a `Pooling`.
 
+    2.2. Five groups of convolutions. The first two groups perform two convolutions, while the last three groups perform three convolutions. The dropout rate of the last convolution in each group is set to 0, which means there is no dropout for this layer.
 
-        2.2. Five groups of convolutions. The first two groups perform two convolutions, while the last three groups perform three convolutions. The dropout rate of the last convolution in each group is set to 0, which means there is no dropout for this layer.
-
-
-        2.3. The last two layers are fully-connected layers of dimension 512.
+    2.3. The last two layers are fully-connected layers of dimension 512.
 
 3. Define Classifier
 
-        The above VGG network extracts high-level features and maps them to a vector of the same size as the categories. Softmax function or classifier is then used for calculating the probability of the image belonging to each category.
+    The above VGG network extracts high-level features and maps them to a vector of the same size as the categories. Softmax function or classifier is then used for calculating the probability of the image belonging to each category.
 
     ```python
     out = paddle.layer.fc(input=net,
@@ -294,7 +292,7 @@ First, we use a VGG network. Since the image size and amount of CIFAR10 are rela
 
 4. Define Loss Function and Outputs
 
-        In the context of supervised learning, labels of training images are defined in `paddle.layer.data` as well. During training, the cross-entropy loss function is used and the loss is the output of the network. During testing, the outputs are the probabilities calculated in the classifier.
+    In the context of supervised learning, labels of training images are defined in `paddle.layer.data` as well. During training, the cross-entropy loss function is used and the loss is the output of the network. During testing, the outputs are the probabilities calculated in the classifier.
 
     ```python
     lbl = paddle.layer.data(

image_classification/index.html → 03.image_classification/index.html

@@ -177,7 +177,7 @@ ResNet(Residual Network) \[[15](#参考文献)\] 是2015年ImageNet图像分类
 
 ## 数据准备
 
-通用图像分类公开的标准数据集常用的有[CIFAR](<https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
+通用图像分类公开的标准数据集常用的有[CIFAR](https://www.cs.toronto.edu/~kriz/cifar.html)、[ImageNet](http://image-net.org/)、[COCO](http://mscoco.org/)等，常用的细粒度图像分类数据集包括[CUB-200-2011](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html)、[Stanford Dog](http://vision.stanford.edu/aditya86/ImageNetDogs/)、[Oxford-flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/)等。其中ImageNet数据集规模相对较大，如[模型概览](#模型概览)一章所讲，大量研究成果基于ImageNet。ImageNet数据从2010年来稍有变化，常用的是ImageNet-2012数据集，该数据集包含1000个类别：训练集包含1,281,167张图片，每个类别数据732至1300张不等，验证集包含50,000张图片，平均每个类别50张图片。
 
 由于ImageNet数据集较大，下载和训练较慢，为了方便大家学习，我们使用[CIFAR10](<https://www.cs.toronto.edu/~kriz/cifar.html>)数据集。CIFAR10数据集包含60,000张32x32的彩色图片，10个类别，每个类包含6,000张。其中50,000张图片作为训练集，10000张作为测试集。图11从每个类别中随机抽取了10张图片，展示了所有的类别。
 
@@ -262,7 +262,7 @@ paddle.init(use_gpu=False, trainer_count=1)
         return fc2
     ```
 
-    2.1. 首先定义了一组卷积网络，即conv_block。卷积核大小为3x3，池化窗口大小为2x2，窗口滑动大小为2，groups决定每组VGG模块是几次连续的卷积操作，dropouts指定Dropout操作的概率。所使用的`img_conv_group`是在`paddle.networks`中预定义的模块，由若干组 `Conv->BN->ReLu->Dropout` 和 一组 `Pooling` 组成，
+    2.1. 首先定义了一组卷积网络，即conv_block。卷积核大小为3x3，池化窗口大小为2x2，窗口滑动大小为2，groups决定每组VGG模块是几次连续的卷积操作，dropouts指定Dropout操作的概率。所使用的`img_conv_group`是在`paddle.networks`中预定义的模块，由若干组 Conv->BN->ReLu->Dropout 和 一组 Pooling 组成。
 
     2.2. 五组卷积操作，即 5个conv_block。 第一、二组采用两次连续的卷积操作。第三、四、五组采用三次连续的卷积操作。每组最后一个卷积后面Dropout概率为0，即不使用Dropout操作。
 

understand_sentiment/README.en.md → 05.understand_sentiment/README.en.md

@@ -334,7 +334,7 @@ def event_handler(event):
             sys.stdout.write('.')
             sys.stdout.flush()
     if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(reader=test_reader, reader_dict=reader_dict)
+        result = trainer.test(reader=test_reader, feeding=feeding)
         print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 ```
 

understand_sentiment/index.en.html → 05.understand_sentiment/index.en.html

@@ -376,7 +376,7 @@ def event_handler(event):
             sys.stdout.write('.')
             sys.stdout.flush()
     if isinstance(event, paddle.event.EndPass):
-        result = trainer.test(reader=test_reader, reader_dict=reader_dict)
+        result = trainer.test(reader=test_reader, feeding=feeding)
         print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 ```