From 8a7d2db5aed89882aaa5f041b21b73d8d29c1d7a Mon Sep 17 00:00:00 2001 From: xiaoting <31891223+tink2123@users.noreply.github.com> Date: Thu, 16 Jan 2020 11:12:16 +0800 Subject: [PATCH] Cherry pick for paddle 1.6 (#843) --- 02.recognize_digits/README.cn.md | 35 +++++++++++++++++++++++++-- 02.recognize_digits/README.md | 34 ++++++++++++++++++++++++-- 02.recognize_digits/index.cn.html | 35 +++++++++++++++++++++++++-- 02.recognize_digits/index.html | 34 ++++++++++++++++++++++++-- 03.image_classification/README.cn.md | 4 +-- 03.image_classification/README.md | 4 +-- 03.image_classification/index.cn.html | 4 +-- 03.image_classification/index.html | 4 +-- 8 files changed, 138 insertions(+), 16 deletions(-) diff --git a/02.recognize_digits/README.cn.md b/02.recognize_digits/README.cn.md index b362119..7f00676 100644 --- a/02.recognize_digits/README.cn.md +++ b/02.recognize_digits/README.cn.md @@ -239,6 +239,37 @@ def multilayer_perceptron(): return prediction ``` +- 卷积池化层：在LeNet-5中会出现多个卷积-池化的操作，为避免代码重复书写，将串联的卷积-池化写成conv_pool函数。 + +```python +def conv_pool(input, num_filters, filter_size, pool_size, pool_stride, act="relu"): + """ + 定义卷积池化层： + 含有一个卷积层和一个池化层 + Args： + input —— 网络输入 + num_filters —— 卷积核的个数 + filter_size —— 卷积核的大小 + pool_size —— 池化核的大小 + pool_stride —— 池化的步长 + act —— 卷积层的激活函数 + + Return: + out -- 经过卷积池化后的特征图 + """ + conv_out = fluid.layers.conv2d( + input=input, + num_filters=num_filters, + filter_size=filter_size, + act=act) + out = fluid.layers.pool2d( + input=conv_out, + pool_size=pool_size, + pool_stride=pool_stride) + return out +``` + + - 卷积神经网络LeNet-5: 输入的二维图像，首先经过两次卷积层到池化层，再经过全连接层，最后使用以softmax为激活函数的全连接层作为输出层。 ```python @@ -254,7 +285,7 @@ def convolutional_neural_network(): img = fluid.data(name='img', shape=[None, 1, 28, 28], dtype='float32') # 第一个卷积-池化层 # 使用20个5*5的滤波器，池化大小为2，池化步长为2，激活函数为Relu - conv_pool_1 = fluid.nets.simple_img_conv_pool( + conv_pool_1 = conv_pool( input=img, filter_size=5, num_filters=20, @@ -264,7 +295,7 @@ def convolutional_neural_network(): conv_pool_1 = fluid.layers.batch_norm(conv_pool_1) # 第二个卷积-池化层 # 使用50个5*5的滤波器，池化大小为2，池化步长为2，激活函数为Relu - conv_pool_2 = fluid.nets.simple_img_conv_pool( + conv_pool_2 = conv_pool( input=conv_pool_1, filter_size=5, num_filters=50, diff --git a/02.recognize_digits/README.md b/02.recognize_digits/README.md index 47691ef..cd9ec16 100644 --- a/02.recognize_digits/README.md +++ b/02.recognize_digits/README.md @@ -218,6 +218,36 @@ def multilayer_perceptron(): return prediction ``` +-Conv_pool layer: LeNet-5 has multiple convolution-pooling operations. In order to avoid repeated code writing, the convolution-pooling in series is written as conv_pool function. + +```python +def conv_pool(input, num_filters, filter_size, pool_size, pool_stride, act="relu"): + """ + Define convolution-pooling layer： + Conv_pool layer has a convolutional layer and a pooling layer + Args： + input —— Input + num_filters —— The number of filter + filter_size —— The filter size + pool_size —— The pool kernel size + pool_stride —— The pool stride size + act —— Activation type + + Return: + out -- output + """ + conv_out = fluid.layers.conv2d( + input=input, + num_filters=num_filters, + filter_size=filter_size, + act=act) + out = fluid.layers.pool2d( + input=conv_out, + pool_size=pool_size, + pool_stride=pool_stride) + return out + +``` -Convolutional neural network LeNet-5: The input two-dimensional image first passes through two convolutional layers to the pooling layer, then passes through the fully connected layer, and finally fully connection layer with softmax as activation function is used as output layer. ```python @@ -233,7 +263,7 @@ def convolutional_neural_network(): img = fluid.data(name='img', shape=[None, 1, 28, 28], dtype='float32') # the first convolution-pooling layer # Use 20 5*5 filters, the pooling size is 2, the pooling step is 2, and the activation function is Relu. - conv_pool_1 = fluid.nets.simple_img_conv_pool( + conv_pool_1 = conv_pool( input=img, filter_size=5, num_filters=20, @@ -243,7 +273,7 @@ def convolutional_neural_network(): conv_pool_1 = fluid.layers.batch_norm(conv_pool_1) # the second convolution-pooling layer # Use 20 5*5 filters, the pooling size is 2, the pooling step is 2, and the activation function is Relu. - conv_pool_2 = fluid.nets.simple_img_conv_pool( + conv_pool_2 = conv_pool( input=conv_pool_1, filter_size=5, num_filters=50, diff --git a/02.recognize_digits/index.cn.html b/02.recognize_digits/index.cn.html index d3f82cd..6473f70 100644 --- a/02.recognize_digits/index.cn.html +++ b/02.recognize_digits/index.cn.html @@ -281,6 +281,37 @@ def multilayer_perceptron(): return prediction ``` +- 卷积池化层：在LeNet-5中会出现多个卷积-池化的操作，为避免代码重复书写，将串联的卷积-池化写成conv_pool函数。 + +```python +def conv_pool(input, num_filters, filter_size, pool_size, pool_stride, act="relu"): + """ + 定义卷积池化层： + 含有一个卷积层和一个池化层 + Args： + input —— 网络输入 + num_filters —— 卷积核的个数 + filter_size —— 卷积核的大小 + pool_size —— 池化核的大小 + pool_stride —— 池化的步长 + act —— 卷积层的激活函数 + + Return: + out -- 经过卷积池化后的特征图 + """ + conv_out = fluid.layers.conv2d( + input=input, + num_filters=num_filters, + filter_size=filter_size, + act=act) + out = fluid.layers.pool2d( + input=conv_out, + pool_size=pool_size, + pool_stride=pool_stride) + return out +``` + + - 卷积神经网络LeNet-5: 输入的二维图像，首先经过两次卷积层到池化层，再经过全连接层，最后使用以softmax为激活函数的全连接层作为输出层。 ```python @@ -296,7 +327,7 @@ def convolutional_neural_network(): img = fluid.data(name='img', shape=[None, 1, 28, 28], dtype='float32') # 第一个卷积-池化层 # 使用20个5*5的滤波器，池化大小为2，池化步长为2，激活函数为Relu - conv_pool_1 = fluid.nets.simple_img_conv_pool( + conv_pool_1 = conv_pool( input=img, filter_size=5, num_filters=20, @@ -306,7 +337,7 @@ def convolutional_neural_network(): conv_pool_1 = fluid.layers.batch_norm(conv_pool_1) # 第二个卷积-池化层 # 使用50个5*5的滤波器，池化大小为2，池化步长为2，激活函数为Relu - conv_pool_2 = fluid.nets.simple_img_conv_pool( + conv_pool_2 = conv_pool( input=conv_pool_1, filter_size=5, num_filters=50, diff --git a/02.recognize_digits/index.html b/02.recognize_digits/index.html index 04ff588..e8057ef 100644 --- a/02.recognize_digits/index.html +++ b/02.recognize_digits/index.html @@ -260,6 +260,36 @@ def multilayer_perceptron(): return prediction ``` +-Conv_pool layer: LeNet-5 has multiple convolution-pooling operations. In order to avoid repeated code writing, the convolution-pooling in series is written as conv_pool function. + +```python +def conv_pool(input, num_filters, filter_size, pool_size, pool_stride, act="relu"): + """ + Define convolution-pooling layer： + Conv_pool layer has a convolutional layer and a pooling layer + Args： + input —— Input + num_filters —— The number of filter + filter_size —— The filter size + pool_size —— The pool kernel size + pool_stride —— The pool stride size + act —— Activation type + + Return: + out -- output + """ + conv_out = fluid.layers.conv2d( + input=input, + num_filters=num_filters, + filter_size=filter_size, + act=act) + out = fluid.layers.pool2d( + input=conv_out, + pool_size=pool_size, + pool_stride=pool_stride) + return out + +``` -Convolutional neural network LeNet-5: The input two-dimensional image first passes through two convolutional layers to the pooling layer, then passes through the fully connected layer, and finally fully connection layer with softmax as activation function is used as output layer. ```python @@ -275,7 +305,7 @@ def convolutional_neural_network(): img = fluid.data(name='img', shape=[None, 1, 28, 28], dtype='float32') # the first convolution-pooling layer # Use 20 5*5 filters, the pooling size is 2, the pooling step is 2, and the activation function is Relu. - conv_pool_1 = fluid.nets.simple_img_conv_pool( + conv_pool_1 = conv_pool( input=img, filter_size=5, num_filters=20, @@ -285,7 +315,7 @@ def convolutional_neural_network(): conv_pool_1 = fluid.layers.batch_norm(conv_pool_1) # the second convolution-pooling layer # Use 20 5*5 filters, the pooling size is 2, the pooling step is 2, and the activation function is Relu. - conv_pool_2 = fluid.nets.simple_img_conv_pool( + conv_pool_2 = conv_pool( input=conv_pool_1, filter_size=5, num_filters=50, diff --git a/03.image_classification/README.cn.md b/03.image_classification/README.cn.md index 9a66a03..53701d3 100644 --- a/03.image_classification/README.cn.md +++ b/03.image_classification/README.cn.md @@ -339,7 +339,7 @@ def train_program(): cost = fluid.layers.cross_entropy(input=predict, label=label) avg_cost = fluid.layers.mean(cost) accuracy = fluid.layers.accuracy(input=predict, label=label) - return [avg_cost, accuracy] + return [avg_cost, accuracy, predict] ``` ## Optimizer Function 配置 @@ -384,7 +384,7 @@ feed_order = ['pixel', 'label'] main_program = fluid.default_main_program() star_program = fluid.default_startup_program() -avg_cost, acc = train_program() +avg_cost, acc, predict = train_program() # Test program test_program = main_program.clone(for_test=True) diff --git a/03.image_classification/README.md b/03.image_classification/README.md index bdeea44..6471b33 100644 --- a/03.image_classification/README.md +++ b/03.image_classification/README.md @@ -339,7 +339,7 @@ def train_program(): cost = fluid.layers.cross_entropy(input=predict, label=label) avg_cost = fluid.layers.mean(cost) accuracy = fluid.layers.accuracy(input=predict, label=label) - return [avg_cost, accuracy] + return [avg_cost, accuracy, predict] ``` ## Optimizer Function Configuration @@ -387,7 +387,7 @@ feed_order = ['pixel', 'label'] main_program = fluid.default_main_program() star_program = fluid.default_startup_program() -avg_cost, acc = train_program() +avg_cost, acc, predict = train_program() # Test program test_program = main_program.clone(for_test=True) diff --git a/03.image_classification/index.cn.html b/03.image_classification/index.cn.html index c41ceca..6c53ac5 100644 --- a/03.image_classification/index.cn.html +++ b/03.image_classification/index.cn.html @@ -381,7 +381,7 @@ def train_program(): cost = fluid.layers.cross_entropy(input=predict, label=label) avg_cost = fluid.layers.mean(cost) accuracy = fluid.layers.accuracy(input=predict, label=label) - return [avg_cost, accuracy] + return [avg_cost, accuracy, predict] ``` ## Optimizer Function 配置 @@ -426,7 +426,7 @@ feed_order = ['pixel', 'label'] main_program = fluid.default_main_program() star_program = fluid.default_startup_program() -avg_cost, acc = train_program() +avg_cost, acc, predict = train_program() # Test program test_program = main_program.clone(for_test=True) diff --git a/03.image_classification/index.html b/03.image_classification/index.html index e30ad0e..66c1a65 100644 --- a/03.image_classification/index.html +++ b/03.image_classification/index.html @@ -381,7 +381,7 @@ def train_program(): cost = fluid.layers.cross_entropy(input=predict, label=label) avg_cost = fluid.layers.mean(cost) accuracy = fluid.layers.accuracy(input=predict, label=label) - return [avg_cost, accuracy] + return [avg_cost, accuracy, predict] ``` ## Optimizer Function Configuration @@ -429,7 +429,7 @@ feed_order = ['pixel', 'label'] main_program = fluid.default_main_program() star_program = fluid.default_startup_program() -avg_cost, acc = train_program() +avg_cost, acc, predict = train_program() # Test program test_program = main_program.clone(for_test=True) -- GitLab