1.建立一個神經網絡添加層

輸入值、輸入的大小、輸出的大小和激勵函數

學過神經網絡的人看下面這個圖就明白了，不懂的去看看我的另一篇博客（http://www.cnblogs.com/wjy-lulu/p/6547542.html）

def add_layer(inputs , in_size , out_size , activate = None):

Weights = tf.Variable(tf.random_normal([in_size,out_size]))#隨機初始化

baises = tf.Variable(tf.zeros([1,out_size])+0.1)#可以隨機但是不要初始化為0，都為固定值比隨機好點

y = tf.matmul(inputs, Weights) + baises #matmul:矩陣乘法，multipy:一般是數量的乘法

if activate:

y = activate(y)

return y

2.訓練一個二次函數

import tensorflow as tf

import numpy as np

def add_layer(inputs , in_size , out_size , activate = None):

Weights = tf.Variable(tf.random_normal([in_size,out_size]))#隨機初始化

baises = tf.Variable(tf.zeros([1,out_size])+0.1)#可以隨機但是不要初始化為0，都為固定值比隨機好點

y = tf.matmul(inputs, Weights) + baises #matmul:矩陣乘法，multipy:一般是數量的乘法

if activate:

y = activate(y)

return y

if __name__ == '__main__':

x_data = np.linspace(-1,1,300,dtype=np.float32)[:,np.newaxis]#創建-1,1的300個數，此時為一維矩陣，后面轉化為二維矩陣===[1,2,3]-->>[[1,2,3]]

noise = np.random.normal(0,0.05,x_data.shape).astype(np.float32)#噪聲是(1,300)格式,0-0.05大小

y_data = np.square(x_data) - 0.5 + noise #帶有噪聲的拋物線

xs = tf.placeholder(tf.float32,[None,1]) #外界輸入數據

ys = tf.placeholder(tf.float32,[None,1])

l1 = add_layer(xs,1,10,activate=tf.nn.relu)

prediction = add_layer(l1,10,1,activate=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),reduction_indices=[1]))#誤差

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)#對誤差進行梯度優化，步伐為0.1

sess = tf.Session()

sess.run( tf.global_variables_initializer())

for i in range(1000):

sess.run(train_step, feed_dict={xs: x_data, ys: y_data})#訓練

if i%50 == 0:

print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))#查看誤差

3.動態顯示訓練過程

顯示的步驟程序之中部分進行說明，其它說明請看其它博客（http://www.cnblogs.com/wjy-lulu/p/7735987.html）

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

def add_layer(inputs , in_size , out_size , activate = None):

Weights = tf.Variable(tf.random_normal([in_size,out_size]))#隨機初始化

baises = tf.Variable(tf.zeros([1,out_size])+0.1)#可以隨機但是不要初始化為0，都為固定值比隨機好點

y = tf.matmul(inputs, Weights) + baises #matmul:矩陣乘法，multipy:一般是數量的乘法

if activate:

y = activate(y)

return y

if __name__ == '__main__':

x_data = np.linspace(-1,1,300,dtype=np.float32)[:,np.newaxis]#創建-1,1的300個數，此時為一維矩陣，后面轉化為二維矩陣===[1,2,3]-->>[[1,2,3]]

noise = np.random.normal(0,0.05,x_data.shape).astype(np.float32)#噪聲是(1,300)格式,0-0.05大小

y_data = np.square(x_data) - 0.5 + noise #帶有噪聲的拋物線

fig = plt.figure('show_data')# figure("data")指定圖表名稱

ax = fig.add_subplot(111)

ax.scatter(x_data,y_data)

plt.ion()

plt.show()

xs = tf.placeholder(tf.float32,[None,1]) #外界輸入數據

ys = tf.placeholder(tf.float32,[None,1])

l1 = add_layer(xs,1,10,activate=tf.nn.relu)

prediction = add_layer(l1,10,1,activate=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),reduction_indices=[1]))#誤差

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)#對誤差進行梯度優化，步伐為0.1

sess = tf.Session()

sess.run( tf.global_variables_initializer())

for i in range(1000):

sess.run(train_step, feed_dict={xs: x_data, ys: y_data})#訓練

if i%50 == 0:

try:

ax.lines.remove(lines[0])

except Exception:

pass

prediction_value = sess.run(prediction, feed_dict={xs: x_data})

lines = ax.plot(x_data,prediction_value,"r",lw = 3)

print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))#查看誤差

plt.pause(2)

while True:

plt.pause(0.01)

4.TensorBoard整體結構化顯示

A.利用with tf.name_scope("name")創建大結構、利用函數的name="name"去創建小結構：tf.placeholder(tf.float32,[None,1],name="x_data")

B.利用writer = tf.summary.FileWriter("G:/test/",graph=sess.graph)創建一個graph文件

C.利用TessorBoard去執行這個文件

這里得注意--->>>首先到你存放文件的上一個目錄--->>然后再去運行這個文件

tensorboard --logdir=test

(被屏蔽的GIF動圖，具體安裝操作歡迎戳“原文鏈接”哈！)

5.TensorBoard局部結構化顯示

A. tf.summary.histogram(layer_name+"Weight",Weights)：直方圖顯示

B. tf.summary.scalar("Loss",loss):折線圖顯示，loss的走向決定你的網絡訓練的好壞，至關重要一點

C.初始化與運行設定的圖表

merge = tf.summary.merge_all()#合并圖表2 writer = tf.summary.FileWriter("G:/test/",graph=sess.graph)#寫進文件3 result = sess.run(merge,feed_dict={xs:x_data,ys:y_data})#運行打包的圖表merge4 writer.add_summary(result,i)#寫入文件，并且單步長50

完整代碼及顯示效果：

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

def add_layer(inputs , in_size , out_size , n_layer = 1 , activate = None):

layer_name = "layer" + str(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")#隨機初始化

tf.summary.histogram(layer_name+"Weight",Weights)

with tf.name_scope("Baises"):

baises = tf.Variable(tf.zeros([1,out_size])+0.1,name="B")#可以隨機但是不要初始化為0，都為固定值比隨機好點

tf.summary.histogram(layer_name+"Baises",baises)

y = tf.matmul(inputs, Weights) + baises #matmul:矩陣乘法，multipy:一般是數量的乘法

if activate:

y = activate(y)

tf.summary.histogram(layer_name+"y_sum",y)

return y

if __name__ == '__main__':

x_data = np.linspace(-1,1,300,dtype=np.float32)[:,np.newaxis]#創建-1,1的300個數，此時為一維矩陣，后面轉化為二維矩陣===[1,2,3]-->>[[1,2,3]]

noise = np.random.normal(0,0.05,x_data.shape).astype(np.float32)#噪聲是(1,300)格式,0-0.05大小

y_data = np.square(x_data) - 0.5 + noise #帶有噪聲的拋物線

fig = plt.figure('show_data')# figure("data")指定圖表名稱

ax = fig.add_subplot(111)

ax.scatter(x_data,y_data)

plt.ion()

plt.show()

with tf.name_scope("inputs"):

xs = tf.placeholder(tf.float32,[None,1],name="x_data") #外界輸入數據

ys = tf.placeholder(tf.float32,[None,1],name="y_data")

l1 = add_layer(xs,1,10,n_layer=1,activate=tf.nn.relu)

prediction = add_layer(l1,10,1,n_layer=2,activate=None)

with tf.name_scope("loss"):

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),reduction_indices=[1]))#誤差

tf.summary.scalar("Loss",loss)

with tf.name_scope("train_step"):

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)#對誤差進行梯度優化，步伐為0.1

sess = tf.Session()

merge = tf.summary.merge_all()#合并

writer = tf.summary.FileWriter("G:/test/",graph=sess.graph)

sess.run( tf.global_variables_initializer())

for i in range(1000):

sess.run(train_step, feed_dict={xs: x_data, ys: y_data})#訓練

if i%100 == 0:

result = sess.run(merge,feed_dict={xs:x_data,ys:y_data})#運行打包的圖表merge

writer.add_summary(result,i)#寫入文件，并且單步長50