一个简单的神经网络例子

神经系统的搭建

import tensorflow as tf
import numpy as np
import matplotlib,pylab as plt

def add_layer(input,in_size,out_size,activation_function = None):
    Weights = tf.Variable(tf.random_normal([in_size,out_size]))
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)
    Wx_plus_b = tf.matmul(input,Weights)+biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

#输入层到神经层
x_data = np.linspace(-1,1,300)[:,np.newaxis]   #产生等差数列
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data)-0.5+noise               #对x_data进行平方
xs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])

#神经层到输出层
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))   #将每个y_data-prediction值取平方，然后求和后去平均值

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()   #使程序不暂停，图像可变动
plt.show()

for i in range(1000):
    sess.run(train_step,feed_dict ={xs:x_data,ys:y_data} )
    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 = 5)

        plt.pause(0.1)
        #print(sess.run(loss,feed_dict ={xs:x_data,ys:y_data}))```

将其可视化

import numpy as np
import matplotlib,pylab as plt

def add_layer(input,in_size,out_size,n_layer,activation_function = None):
    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)
                 tf.summary.histogram(layer_name + '/biases', biases)
            with tf.name_scope('Wx_plus_b'):
                Wx_plus_b = tf.matmul(input,Weights)+biases
            if activation_function is None:
                outputs = Wx_plus_b
                tf.summary.histogram(layer_name + '/outputs', outputs)
            else:
                outputs = activation_function(Wx_plus_b)
            return outputs

#输入层到神经层
x_data = np.linspace(-1,1,300)[:,np.newaxis]   #产生等差数列
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data)-0.5+noise               #对x_data进行平方

with tf.name_scope('input'):
    xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
    ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

**将其可视化**
l1 = add_layer(xs,1,10,n_layer = 1,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,n_layer = 2,activation_function=None)

with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))   #将每个y_data-prediction值取平方，然后求和后去平均值
    tf.summary.scalar('loss',loss)   #event图
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()
sess = tf.Session()
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter("C:/Users/Administrator/Desktop/model",sess.graph)
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})
        writer.add_summary(result,i)

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()   #使程序不暂停，图像可变动
plt.show()

for i in range(1000):
    sess.run(train_step,feed_dict ={xs:x_data,ys:y_data} )
    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 = 5)

        plt.pause(0.1)
        #print(sess.run(loss,feed_dict ={xs:x_data,ys:y_data}))

步骤1：

步骤2：