# -*- coding: utf-8 -*-
"""
@Time ： 2021/8/14 上午1:42
@Auth ： 陈伟峰
@File ：tensorflow_01.py
@phone: 15882085601
@IDE ：PyCharm
@Motto：ABC(Always Be Coding)

"""
import tensorflow as tf
import numpy as np

# 构造300个点
x_data = np.linspace(-1,1,300)[:,np.newaxis]
# print(x_data)
# 随机噪声
noise = np.random.normal(0,0.05,x_data.shape)
# print(noise.shape)

y_data = np.square(x_data)-0.5+noise
# print(y_data.shape)

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


def add_layer(inputs,in_size,out_size,activation_function=None):
    '''
    :param inputs:输入数据
    :param in_size: 输入大小
    :param out_size: 输出大小
    :param activation_function:激活函数
    :return:
    '''
    # 构建权重
    weights = tf.Variable(tf.random_normal([in_size,out_size]))
    # 构建bias
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)
    # 矩阵乘法
    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

# 构建隐藏层
h1 = add_layer(xs,1,20,activation_function=tf.nn.relu)
# 构建输出层
predict = add_layer(h1,20,1,activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-predict),reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(loss)


init = tf.global_variables_initializer()
with tf.Session() as sess:
    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("loss=",sess.run(loss,feed_dict={
                xs:x_data,
                ys:y_data
            }))