第十六节，使用函数封装库tf.contrib.layers

这一节，介绍TensorFlow中的一个封装好的高级库，里面有前面讲过的不少函数的高级封装，使用这个高级库来开发程序将会提升效率。

咱们改写第十三节的程序，卷积函数咱们使用tf.contrib.layers.conv2d()，池化函数使用tf.contrib.layers.max_pool2d()和tf.contrib.layers.avg_pool2d()，全链接函数使用tf.contrib.layers.fully_connected()。

一 tf.contrib.layers中的具体函数介绍

1.tf.contrib.layers.conv2d()函数的定义以下：

def convolution(inputs, num_outputs, kernel_size, stride=1, padding='SAME', data_format=None, rate=1, activation_fn=nn.relu, normalizer_fn=None, normalizer_params=None, weights_initializer=initializers.xavier_initializer(), weights_regularizer=None, biases_initializer=init_ops.zeros_initializer(), biases_regularizer=None, reuse=None, variables_collections=None, outputs_collections=None, trainable=True, scope=None):

经常使用的参数说明以下：

• inputs:形状为[batch_size, height, width, channels]的输入。
• num_outputs：表明输出几个channel。这里不须要再指定输入的channel了，由于函数会自动根据inpus的shpe去判断。
• kernel_size：卷积核大小，不须要带上batch和channel，只须要输入尺寸便可。[5,5]就表明5x5的卷积核，若是长和宽都同样，也能够只写一个数5.
• stride：步长，默认是长宽都相等的步长。卷积时，通常都用1，因此默认值也是1.若是长和宽都不相等，也能够用一个数组[1,2]。
• padding：填充方式，'SAME'或者'VALID'。
• activation_fn：激活函数。默认是ReLU。也能够设置为None
• weights_initializer：权重的初始化，默认为initializers.xavier_initializer()函数。
• weights_regularizer：权重正则化项，能够加入正则函数。biases_initializer：偏置的初始化，默认为init_ops.zeros_initializer()函数。
• biases_regularizer：偏置正则化项，能够加入正则函数。
• trainable：是否可训练，如做为训练节点，必须设置为True，默认便可。若是咱们是微调网络，有时候须要冻结某一层的参数，则设置为False。

2.tf.contrib.layers.max_pool2d()函数的定义以下：

def max_pool2d(inputs, kernel_size, stride=2, padding='VALID', data_format=DATA_FORMAT_NHWC, outputs_collections=None, scope=None):

参数说明以下：

• inputs: A 4-D tensor of shape `[batch_size, height, width, channels]` if`data_format` is `NHWC`, and `[batch_size, channels, height, width]` if `data_format` is `NCHW`.
• kernel_size: A list of length 2: [kernel_height, kernel_width] of the pooling kernel over which the op is computed. Can be an int if both values are the same.
• stride: A list of length 2: [stride_height, stride_width].Can be an int if both strides are the same. Note that presently both strides must have the same value.
• padding: The padding method, either 'VALID' or 'SAME'.
• data_format: A string. `NHWC` (default) and `NCHW` are supported.
• outputs_collections: The collections to which the outputs are added.
• scope: Optional scope for name_scope.

3.tf.contrib.layers.avg_pool2d()函数定义

 

def avg_pool2d(inputs, kernel_size, stride=2, padding='VALID', data_format=DATA_FORMAT_NHWC, outputs_collections=None, scope=None):

参数说明以下：

• inputs: A 4-D tensor of shape `[batch_size, height, width, channels]` if`data_format` is `NHWC`, and `[batch_size, channels, height, width]` if `data_format` is `NCHW`.
• kernel_size: A list of length 2: [kernel_height, kernel_width] of the pooling kernel over which the op is computed. Can be an int if both values are the same.
• stride: A list of length 2: [stride_height, stride_width].Can be an int if both strides are the same. Note that presently both strides must have the same value.
• padding: The padding method, either 'VALID' or 'SAME'.
• data_format: A string. `NHWC` (default) and `NCHW` are supported.
• outputs_collections: The collections to which the outputs are added.
• scope: Optional scope for name_scope.

4.tf.contrib.layers.fully_connected()函数的定义以下：

def fully_connected(inputs, num_outputs, activation_fn=nn.relu, normalizer_fn=None, normalizer_params=None, weights_initializer=initializers.xavier_initializer(), weights_regularizer=None, biases_initializer=init_ops.zeros_initializer(), biases_regularizer=None, reuse=None, variables_collections=None, outputs_collections=None, trainable=True, scope=None):

参数说明以下：

• inputs: A tensor of at least rank 2 and static value for the last dimension; i.e. `[batch_size, depth]`, `[None, None, None, channels]`.
• num_outputs: Integer or long, the number of output units in the layer.
• activation_fn: Activation function. The default value is a ReLU function.Explicitly set it to None to skip it and maintain a linear activation.
• normalizer_fn: Normalization function to use instead of `biases`. If `normalizer_fn` is provided then `biases_initializer` and
• `biases_regularizer` are ignored and `biases` are not created nor added.default set to None for no normalizer function
• normalizer_params: Normalization function parameters.
• weights_initializer: An initializer for the weights.
• weights_regularizer: Optional regularizer for the weights.
• biases_initializer: An initializer for the biases. If None skip biases.
• biases_regularizer: Optional regularizer for the biases.
• reuse: Whether or not the layer and its variables should be reused. To be able to reuse the layer scope must be given.
• variables_collections: Optional list of collections for all the variables or a dictionary containing a different list of collections per variable.
• outputs_collections: Collection to add the outputs.
• trainable: If `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see tf.Variable).若是咱们是微调网络，有时候须要冻结某一层的参数，则设置为False。
• scope: Optional scope for variable_scope.

 

二 改写cifar10分类

代码以下：

# -*- coding: utf-8 -*-
""" Created on Thu May 3 12:29:16 2018 @author: zy """

''' 创建一个带有全链接层的卷积神经网络 并对CIFAR-10数据集进行分类 1.使用2个卷积层的同卷积操做，滤波器大小为5x5，每一个卷积层后面都会跟一个步长为2x2的池化层，滤波器大小为2x2 2.对输出的64个feature map进行全局平均池化，获得64个特征 3.加入一个全链接层，使用softmax激活函数，获得分类 '''

import cifar10_input import tensorflow as tf import numpy as np def print_op_shape(t): ''' 输出一个操做op节点的形状 '''
    print(t.op.name,'',t.get_shape().as_list()) ''' 一 引入数据集 ''' batch_size = 128 learning_rate = 1e-4 training_step = 15000 display_step = 200
#数据集目录
data_dir = './cifar10_data/cifar-10-batches-bin'
print('begin') #获取训练集数据
images_train,labels_train = cifar10_input.inputs(eval_data=False,data_dir = data_dir,batch_size=batch_size) print('begin data') ''' 二 定义网络结构 '''

#定义占位符
input_x = tf.placeholder(dtype=tf.float32,shape=[None,24,24,3])   #图像大小24x24x
input_y = tf.placeholder(dtype=tf.float32,shape=[None,10])        #0-9类别 
 x_image = tf.reshape(input_x,[batch_size,24,24,3]) #1.卷积层 ->池化层
 h_conv1 = tf.contrib.layers.conv2d(inputs=x_image,num_outputs=64,kernel_size=5,stride=1,padding='SAME', activation_fn=tf.nn.relu)    #输出为[-1,24,24,64]
print_op_shape(h_conv1) h_pool1 = tf.contrib.layers.max_pool2d(inputs=h_conv1,kernel_size=2,stride=2,padding='SAME')         #输出为[-1,12,12,64]
print_op_shape(h_pool1) #2.卷积层 ->池化层
 h_conv2 =tf.contrib.layers.conv2d(inputs=h_pool1,num_outputs=64,kernel_size=[5,5],stride=[1,1],padding='SAME', activation_fn=tf.nn.relu)    #输出为[-1,12,12,64]
print_op_shape(h_conv2) h_pool2 =  tf.contrib.layers.max_pool2d(inputs=h_conv2,kernel_size=[2,2],stride=[2,2],padding='SAME')   #输出为[-1,6,6,64]
print_op_shape(h_pool2) #3全链接层
 nt_hpool2 = tf.contrib.layers.avg_pool2d(inputs=h_pool2,kernel_size=6,stride=6,padding='SAME')          #输出为[-1,1,1,64]
print_op_shape(nt_hpool2) nt_hpool2_flat = tf.reshape(nt_hpool2,[-1,64]) y_conv = tf.contrib.layers.fully_connected(inputs=nt_hpool2_flat,num_outputs=10,activation_fn=tf.nn.softmax) print_op_shape(y_conv) ''' 三 定义求解器 '''

#softmax交叉熵代价函数
cost = tf.reduce_mean(-tf.reduce_sum(input_y * tf.log(y_conv),axis=1)) #求解器
train = tf.train.AdamOptimizer(learning_rate).minimize(cost) #返回一个准确度的数据
correct_prediction = tf.equal(tf.arg_max(y_conv,1),tf.arg_max(input_y,1)) #准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,dtype=tf.float32)) ''' 四 开始训练 ''' sess = tf.Session(); sess.run(tf.global_variables_initializer()) # 启动计算图中全部的队列线程 调用tf.train.start_queue_runners来将文件名填充到队列，不然read操做会被阻塞到文件名队列中有值为止。
tf.train.start_queue_runners(sess=sess) for step in range(training_step): #获取batch_size大小数据集
    image_batch,label_batch = sess.run([images_train,labels_train]) #one hot编码
    label_b = np.eye(10,dtype=np.float32)[label_batch] #开始训练
    train.run(feed_dict={input_x:image_batch,input_y:label_b},session=sess) if step % display_step == 0: train_accuracy = accuracy.eval(feed_dict={input_x:image_batch,input_y:label_b},session=sess) print('Step {0} tranining accuracy {1}'.format(step,train_accuracy))