TensorFlow入门：实现简单的神经网络并用matplotlib.pyplot可视化

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/5/14 13:40
# @Author  : HJH
# @Site    : 
# @File    : add_layer.py
# @Software: PyCharm

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

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

if __name__=='__main__':
    #创建一个300行的等差数列
    X=np.linspace(-1,1,300)[:,np.newaxis]
    noise=np.random.normal(0,0.05,X.shape)
    y=np.square(X)-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)
    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()

    #使用matplotlib.pyplot可视化
    with tf.Session() as sess:
        sess.run(init)
        fig=plt.figure()
        ax=fig.add_subplot(1,1,1)
        ax.scatter(X,y)
        plt.ion()#
        for i in range(1500):
            sess.run(train_step,feed_dict={xs:X,ys:y})
            if i%50==0:
                # print(sess.run(loss,feed_dict={xs:X,ys:y}))
                try:
                    ax.lines.remove(lines[0])
                except Exception:
                    pass
                prediction_value=sess.run(prediction,feed_dict={xs:X,ys:y})
                lines=ax.plot(X,prediction_value,'r_',lw=5)
                plt.pause(0.1)
        plt.ioff()
        plt.show()