人工智能python的tensorflow基础

import tensorflow as tf
matrix1=tf.constant([[3,3]])
matrix2=tf.constant([[2],
                    [2]])
product=tf.matmul(matrix1,matrix2)
with tf.Session() as sess:#打开Session以sess命名，不用管关不关Session,运行完with里的语句自动关Session
    result2=sess.run(product)
    print("行乘以列:",result2)

#定义变量
import tensorflow as tf
state=tf.Variable(0,name='counter')#Variable(初始值,name='变量名子')
print(state.name)#打印出它的名字
one=tf.constant(1)
new_value=tf.add(state,one)#输出为Tensor("Add_4:0", shape=(), dtype=int32)可见new_value只是一个代表，
                            #并不是真正的值，更像是代表这里的add这个运算过程，
                                                        #其实真正的值实在变量state中。
update=tf.assign(state,new_value)#将new_value加载到state
init=tf.global_variables_initializer()#激活所有变量
with tf.Session() as sess:
    sess.run(init)
    for _ in range(3):#三次循环
        sess.run(update)
        print(sess.run(state))#必须要用sess这个指针去run一下

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:[8.0]}))##feed_dict与placeholder相对应

import tensorflow as tf 
import numpy as np
def add_layer(inputs,in_size,out_size,activation_function):
  Weights=tf.Variable(tf.random_normal([in_size,out_size]))#定义一个in_siz行，out_size列的矩阵。
                                                           #注：矩阵相乘输出为：前面项的行数，后面项的列数。
  biases=tf.Variable(tf.zeros([1,out_size])+0.1)#定义一个偏置
  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
x_data=np.linspace(-1,1,300)[:,np.newaxis]##这一行中的[:,np.newxis]是将数据在行上增加n多行，列数为1
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])#数据为float32形式
ys=tf.placeholder(tf.float32,[None,1])
l1=add_layer(xs,1,10,activation_function=tf.nn.relu)#用placeholder中传来的值
prediction=add_layer(l1,10,1,activation_function=None)
loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init=tf.initialize_all_variables()
sess=tf.Session()
sess.run(init)
for i in range(1000):
  sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
  if i%100==0:
    print("第%d次："%(i),sess.run(loss,feed_dict={xs:x_data,ys:y_data}))