TensorFlow實戰第四課(tensorboard數據可視化)

 

tensorboard可視化工具

tensorboard是tensorflow的可視化工具，通過這個工具我們可以很清楚的看到整個神經網絡的結構及框架。

通過之前展示的代碼，我們進行修改從而展示其神經網絡結構。

 

一、搭建圖紙

首先對input進行修改，將xs，ys進行新的名稱指定x_in y_in

這里指定的名稱，之后會在可視化圖層中inputs中顯示出來

xs= tf.placeholder(tf.float32, [None, 1],name='x_in')

ys= tf.placeholder(tf.loat32, [None, 1],name='y_in')

 

使用with.tf.name_scope('inputs')可以將xs  ys包含進來，形成一個大的圖層，圖層的名字就是

with.tf.name_scope()方法中的參數

with tf.name_scope('inputs'):
    # define placeholder for inputs to network
    xs = tf.placeholder(tf.float32, [None, 1])
    ys = tf.placeholder(tf.float32, [None, 1])

 

接下來編輯layer

編輯前的代碼片段：

def add_layer(inputs, in_size, out_size, activation_function=None):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    return outputs

編輯后

def add_layer(inputs, in_size, out_size, activation_function=None):
    # add one more layer and return the output of this layer
    with tf.name_scope('layer'):
        Weights= tf.Variable(tf.random_normal([in_size, out_size]))
        # and so on...

 

定義完大的框架layer后，通知需要定義里面小的部件weights biases activationfunction

定義方法有兩種，一是用tf.name_scope（），二是在Weights中指定名稱W

    def add_layer(inputs, in_size, out_size, activation_function=None):
    #define layer name
    with tf.name_scope('layer'):
        #define weights name 
        with tf.name_scope('weights'):
            Weights= tf.Variable(tf.random_normal([in_size, out_size]),name='W')
        #and so on......

 

接着定義biases，方法同上

def add_layer(inputs, in_size, out_size, activation_function=None):
    #define layer name
    with tf.name_scope('layer'):
        #define weights name 
        with tf.name_scope('weights')
            Weights= tf.Variable(tf.random_normal([in_size, out_size]),name='W')
        # define biase
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        # and so on....

 

最后編輯loss 將with.tf.name_scope( )添加在loss上方 並起名為loss

這句話就是繪制了loss

 

 最后再對train_step進行編輯  

with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

 

我們還需要運用tf.summary.FileWriter( )將上面繪畫的圖保存到一個目錄中，方便用瀏覽器瀏覽。

這個方法中的第二個參數需要使用sess.graph。因此我們把這句話放在獲取session后面。

這里的graph是將前面定義的框架信息收集起來，然后放在logs/目錄下面。

sess = tf.Session() # get session
# tf.train.SummaryWriter soon be deprecated, use following
writer = tf.summary.FileWriter("logs/", sess.graph)

 

最后在終端中使用命令獲取網址即可查看

tensorboard --logdir logs

完整代碼：

#如何可視化神經網絡

#tensorboard

import tensorflow as tf


def add_layer(inputs, in_size, out_size, activation_function=None):
    # add one more layer and return the output of this layer
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        return outputs


# define placeholder for inputs to network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
    ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# the error between prediciton and real data
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()


writer = tf.summary.FileWriter("logs/", sess.graph)

init = tf.global_variables_initializer()

sess.run(init)

 

 -------------------------------------------------------------------

tensorflow可視化訓練過程的圖標是如何制作的？

 

 

 首先要添加一些模擬數據。nump可以幫助我們添加一些模擬數據。

利用np.linespace（）產生隨機的數字 同時為了模擬更加真實 我們會添加一些噪聲 這些噪聲是通過np.random.normal（）隨機產生的。

 x_data= np.linspace(-1, 1, 300, dtype=np.float32)[:,np.newaxis]
 noise=  np.random.normal(0, 0.05, x_data.shape).astype(np.float32)
 y_data= np.square(x_data) -0.5+ noise

 

在layer中為weights biases設置變化圖表

首先我們在add_layer（）方法中添加一個參數n_layer 來標識層數 並且用變量layer_name代表其每層的名稱

def add_layer(
    inputs , 
    in_size, 
    out_size,
    n_layer, 
    activation_function=None):
    ## add one more layer and return the output of this layer
    layer_name='layer%s'%n_layer  ## 定義一個新的變量
    ## and so on ……

 

接下來 我們層中的Weights設置變化圖 tensorflow中提供了tf.histogram_summary( )方法，用來繪制圖片，第一個參數是圖表的名稱，第二個參數是圖標要記錄的變量。

def add_layer(inputs , 
            in_size, 
            out_size,n_layer, 
            activation_function=None):
    ## add one more layer and return the output of this layer
    layer_name='layer%s'%n_layer
    with tf.name_scope('layer'):
         with tf.name_scope('weights'):
              Weights= tf.Variable(tf.random_normal([in_size, out_size]),name='W')
              tf.summary.histogram(layer_name + '/weights', Weights) 
    ##and so no ……

 

同樣的方法我們對biases進行繪制圖標：

with tf.name_scope('biases'):
    biases = tf.Variable(tf.zeros([1,out_size])+0.1, name='b')
    tf.summary.histogram(layer_name + '/biases', biases)  

 

至於activation_function( ) 可以不用繪制，我們對output 使用同樣的方法

最后通過修改 addlayer（）方法如下所示

def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
    # add one more layer and return the output of this layer

    #對神經層進行命名
    layer_name = 'layer%s' % n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
            tf.summary.histogram(layer_name + '/weights', Weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')
            tf.summary.histogram(layer_name + '/biases', biases)
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b, )
        tf.summary.histogram(layer_name + '/outputs', outputs)
    return outputs

 

設置loss的變化圖

 loss是tensorb的event下面的 這是由於我們使用的是tf.scalar_summary（）方法。

 

 當你的loss函數圖像呈現的是下降的趨勢 說明學習是有效的

 

將所有訓練圖合並

接下來進行合並打包，tf.merge_all_summaries（）方法會對我們所有的summaries合並到一起

sess = tf.Session()
#合並
merged = tf.summary.merge_all()

writer = tf.summary.FileWriter("logs/", sess.graph)

init = tf.global_variables_initializer()

 

訓練數據

忽略不想寫

完整代碼如下：（運行代碼后需要在終端中執行tensorboard --logdir logs）

import tensorflow as tf
import numpy as np


def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
    # add one more layer and return the output of this layer

    #對神經層進行命名
    layer_name = 'layer%s' % n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
            tf.summary.histogram(layer_name + '/weights', Weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')
            tf.summary.histogram(layer_name + '/biases', biases)
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b, )
        tf.summary.histogram(layer_name + '/outputs', outputs)
    return outputs


# Make up some real data
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
    ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

# add hidden layer
l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None)

# the error between prediciton and real data
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                                        reduction_indices=[1]))
    tf.summary.scalar('loss', loss)

with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.Session()
#合並
merged = tf.summary.merge_all()

writer = tf.summary.FileWriter("logs/", sess.graph)

init = tf.global_variables_initializer()
sess.run(init)

for i in range(1000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        result = sess.run(merged,feed_dict={xs: x_data, ys: y_data})
        #i 就是記錄的步數
        writer.add_summary(result, i)

 

tensorboard查看效果  使用命令tensorboard --logdir logs