Tensorflow 创建神经网络

一个神经网络系统，由很多层组成，输入层用来接收信息，中间层加工处理输入信息，输出层就是计算机对这个输入信息的认知。

https://www.jianshu.com/p/e112012a4b2d

搭建神经网络基本流程

定义添加神经层的函数

1.训练的数据
2.定义节点准备接收数据
3.定义神经层：隐藏层和预测层
4.定义 loss 表达式
5.选择 optimizer 使 loss 达到最小

然后对所有变量进行初始化，通过 sess.run optimizer，迭代 1000 次进行学习：

import tensorflow as tf
import numpy as np

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

    Weight = tf.Variable(tf.random.normal([in_size,out_size]))
    biases  = tf.Variable(tf.zeros([1,out_size])+0.1)
    wx = tf.matmul(inputs,Weight)+biases

    if activation_fuction is None:
        output = wx
    else :
        output = activation_fuction(wx)
    return output 

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])
hidden = add_layer(xs,1,10,activation_fuction =tf.nn.relu)
prediction = add_layer(hidden,10,1,activation_fuction = None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(prediction - ys),reduction_indices=[1]))
train = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for i in range(1000):
#   # training train_step 和 loss 都是由 placeholder 定义的运算，所以这里要用 feed 传入参数
        sess.run(train, feed_dict={xs: x_data, ys: y_data})
        if i%50 == 0:
            print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
    

原文地址：https://www.cnblogs.com/gaona666/p/12632897.html