莫烦 Tensorflow

莫烦的代码第4行是tf.mul但是目前版本没有这个函数了，改成了tf.multiply（表示两个数相乘）
feed_dict这个很好的解决了先构建模型再去输入值得问题
import  tensorflow as tf
input1=tf.placeholder(tf.float32)
input2=tf.placeholder(tf.float32)
output=tf.multiply(input1,input2)
with tf.Session() as sess:
    print(sess.run(output,feed_dict={input1:[7.],input2:[2]}))

  

没调通

import  tensorflow as tf
import  numpy as np
def add_layer(intput,insize,outsize,activative):
    Weight=tf.Variable(tf.random_normal([insize,outsize]))
    Biase=tf.Variable(tf.zeros([1,outsize])+0.1)#设置baise的值全为0.1
    Wx_plus_b=tf.matmul(input,Weight)+Biase
    if activative is None:
        outputs=Wx_plus_b
    else:
        outputs=activative(Wx_plus_b)
    return outputs
x_data=np.linspace(-1,1,300)[:,np.newaxis]#np.linspace创建等差数列，间隔是300[:,np.newaxis]的作用是将此数列变成称300*1的列向量
#加上噪声
xs=tf.placeholder(tf.float32,[None,1])
ys=tf.placeholder(tf.float32,[None,1])
noise=np.random.normal(0,0.05,x_data.shape)#均值是0，方差是0.05，格式与x_data一样
y_data=np.square(x_data)-0.5
print (x_data)
l1=add_layer(xs,1,10,activative=tf.nn.relu)#构建网络
predition=add_layer(l1,10,1,activative=tf.nn.sigmoid)
loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-predition),reduction_indices=[1]))#reduction_indices是将其压缩成一维的
train_step=tf.train.GradientDescentOptimizer(0.05).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%20==0):
            print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))