Tensorflow机器学习5 创建神经网络

1、创建添加层函数

import tensorflow as tf

#P15 例子 https://www.bilibili.com/video/av16001891/?p=15

#添加层
def add_layer(inputs,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(inputs,Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

2、创建神经网络

import tensorflow as tf
import numpy as np

#P15 例子3 https://www.bilibili.com/video/av16001891/?p=15

#添加层
def add_layer(inputs,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(inputs,Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

#P16 例子3 https://www.bilibili.com/video/av16001891/?p=16
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

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

l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)

#square平方
#reduce_sum求和，reduction_indices处理的维度
#reduce_mean求平均值
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction) , reduction_indices=[1]))

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

init = tf.global_variables_initializer()

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

for i in range(1000):
    sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
    if i % 50 == 0:
        print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))

运行结果：

0.07432678
0.020319471
0.008260171
0.0075573986
0.0067263753
0.005967979
0.005414523
0.0050400905
0.0047189826
0.0044596097
0.0042297365
0.0040490534
0.0039058614
0.0037829678
0.0036782217
0.0035844247
0.003500444
0.0034384385
0.003389593
0.0033436806

3、添加可视化

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#P15 例子3 https://www.bilibili.com/video/av16001891/?p=15

#添加层
def add_layer(inputs,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(inputs,Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

#P16 例子3 https://www.bilibili.com/video/av16001891/?p=16
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

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

l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)

#square平方
#reduce_sum求和，reduction_indices处理的维度
#reduce_mean求平均值
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction) , reduction_indices=[1]))

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

init = tf.global_variables_initializer()

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

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()


for i in range(1000):
    sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
    if i % 50 == 0:
        print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))

        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)

plt.ioff()
plt.show()