TF-GD

import tensorflow as tf #导包
##采用线性模型y = w*x+b，实现简单的GD


##模型参数Model parameters
w = tf.Variable([.3],dtype = tf.float32)
b = tf.Variable([-.3],dtype = tf.float32)
learn_rate = 0.01#学习效率
loop = 1000#迭代次数
##模型输入输出，Model input and output
x = tf.placeholder(tf.float32)#占位符
y = tf.placeholder(tf.float32)#占位符
liner = w*x+b#模型

##计算损失函数 calculate the loss
loss = tf.reduce_sum(tf.square(liner-y))#一维张量平方差和
##优化器optimizer 
optimizer = tf.train.GradientDescentOptimizer(learn_rate)#设置学习效率
train = optimizer.minimize(loss)#梯度计算和梯度更新
#此处处理特殊数据时建议将二者操作分开，可以对计算的梯度进行限制，防止梯度消失和爆炸

#training data
x_train = [1,2,3,4]
y_train = [0,-1,-2,-3]

#训练training
init = tf.global_variables_initializer()#初始化参数
#creat the graph 创建图
los = []
step = []
with tf.Session() as sess:
    sess.run(init)
    for i in range(loop):
        sess.run(train,{x:x_train,y:y_train})
        cur_w,cur_b,cur_loss = sess.run([w,b,loss],{x:x_train,y:y_train})
        step.append(i)
        los.append(cur_loss)
        #print("w: %s b: %s loss: %s "%(cur_w,cur_b,cur_loss))
from matplotlib import pyplot as plt
plt.scatter(step,los,color = 'r')
plt.show()