Tensorflow入门之线性回归

# coding=utf-8
import tensorflow as tf
import numpy as np
import matplotlib as mpl
mpl.use('TkAgg')
import matplotlib.pyplot as plt

"""
定义添加层
"""
def add_layer(inputs,in_size,out_size,activation_func=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_func is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_func(Wx_plus_b)
    return outputs

"""
随机生成输入数据，定义一元二次函数，并添加噪点使其更像真实数据
"""
#np.newaxis添加新维度,结果为300*1矩阵
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,ys是为了方便实现batch
其中None表示样本数，1表示样本的维度
"""
xs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])


"""
添加隐藏层和输出层
1，10，1分别表示输入层，隐藏层，输出层神经元的个数
"""
l1 = add_layer(xs,1,10,activation_func=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_func=None)

"""
计算loss
reduction_indices[1]按行求和，reduction_indices[0]按列求和
"""
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

#变量初始化
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

#可视化操作
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)

#打开交互模式
plt.ion()

#训练
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)

#显示前关闭交互模式
plt.ioff()
plt.show()