tensorflow—— 基础中的基础

import tensorflow as tf 

会话打开

m_1 = tf.constant([[3,2]])
m_2 = tf.constant([[3],
                  [2]])
pr = tf.matmul(m_1,m_2)
with tf.Session() as s_1:
    result = s_1.run(pr)
    print(result)

[[13]]

第二种打开方式

s_2 = tf.Session()
result_2 = s_2.run(pr)
print(result_2)
s_2.close()

[[13]]

变量和常量

v_1 = tf.Variable(0,name='counter')  # 设置变量
c_1 = tf.constant(1)  # 设置常量
v_1.name  # 查看v_1属性 

new_value = tf.add(v_1 ,c_1)  # 新的值：变量+常量
update = tf.assign(v_1,new_value)  # 讲new_value传递至v_1  
init = tf.global_variables_initializer()  # 初始化所有变量

with tf.Session() as sess:
    sess.run(init)
    for i in range(3):
        sess.run(update)
        print(sess.run(v_1))
        print(v_1.name)

1
counter_6:0
2
counter_6:0
3
counter_6:0

placeholder

在run时需要传入的数值

holder_1 = tf.placeholder(tf.float32)
holder_2 = tf.placeholder(tf.float32)
result = tf.multiply(holder_1,holder_2)
with tf.Session() as sess:
    print(sess.run(result,feed_dict = {holder_1:[8.],holder_2:[10.]}))

[80.]

激活函数

将线性转为非线性

定义一层

def add_layer(inputs,in_size,out_size,activation_function = None):
    Weights = tf.Variable(tf.random_normal([in_size,out_size]))  # 设置权重
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)  # 常数项
    Wx_b = tf.matmul(inputs,Weights) + biases  # 用权重和biases计算输入
    if activation_function is None:  # 如果存在激活函数则对输出进行激活否则直接输出  
        outputs = Wx_b
    else:
        outputs = activation_function(Wx_b)
    return outputs

搞一个神经网络

import numpy as np
# 创建一个（400,1）的输入和同格式的输出
x_data = np.linspace(-1,1,400).reshape(-1,1)  
noise = np.random.normal(1,0.05,x_data.shape).astype(np.float32)
y_data = np.square(x_data) + noise

xs = tf.placeholder(tf.float32,[None,1])  # 设立 x和y的传入
ys = tf.placeholder(tf.float32,[None,1])
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)  # 建立隐藏层 输入为x_data，输入为（400,10）的输入 激活函数为 relu
pre = add_layer(l1,10,1)  # 建立输出层 输入为隐藏层输入 输出为预测值 没有激活函数 
loss  = tf.reduce_mean(tf.reduce_sum(tf.square(ys-pre), reduction_indices=[1]))  # 设置偏差 
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)  # 设置训练方式 为 梯度下降 目标为最小化loss
init = tf.global_variables_initializer() 
with tf.Session() as sess:
    sess.run(init)
    for step in range(2000):
        sess.run(train_step,feed_dict = {xs:x_data,ys:y_data})
        if step%50 == 0:
            print(sess.run(loss,feed_dict = {xs:x_data,ys:y_data}))

ten可视化