tensorflow(一)

最新推荐文章于 2024-09-20 21:37:25 发布

虎虎1232

最新推荐文章于 2024-09-20 21:37:25 发布

阅读量137

点赞数 1

文章标签： tensorflow

本文链接：https://blog.csdn.net/m0_37619396/article/details/100736342

版权

文章目录

1.tf简介

什么是TensorFlow?
TensorFlow是Google开发的一款神经网络的Python外部的结构包, 也是一个采用数据流图来进行数值计算的开源软件库.TensorFlow 让我们可以先绘制计算结构图, 也可以称是一系列可人机交互的计算操作, 然后把编辑好的Python文件转换成更高效的C++, 并在后端进行计算.

2.GradientDescentOptimizer

import numpy as np
import tensorflow as tf

#create data
x_data=np.random.rand(100).astype(np.float32)
y_data=x_data*0.1+0.3

###create tensorflow structure start###
Weights=tf.Variable(tf.random_uniform([1],-1.0,1.0)) #[1]一维, -1~1是范围
biases=tf.Variable(tf.zeros([1]))

y=Weights*x_data+biases

loss=tf.reduce_mean(tf.square(y-y_data))
optimizer=tf.train.GradientDescentOptimizer(0.5) #学习效率,一般是小于1的数
train=optimizer.minimize(loss)


init=tf.initialize_all_variables() #把结构激活初始化
###create tensorflow structure stop###

sess=tf.Session()
sess.run(init) #very important

for step in range(201):
    sess.run(train)
    if step%20 == 0:
        print(step,sess.run(Weights),sess.run(biases))

结果

0 [-0.20931756] [0.6931524]
20 [0.00141808] [0.35603204]
40 [0.07586616] [0.31371722]
60 [0.09409177] [0.30335814]
80 [0.0985536] [0.30082214]
100 [0.09964592] [0.30020127]
120 [0.09991331] [0.30004928]
140 [0.09997876] [0.30001208]
160 [0.09999479] [0.30000296]
180 [0.09999873] [0.30000073]
200 [0.09999967] [0.3000002]

3.Session

import tensorflow as tf

matrix1=tf.constant([[3,3]])
matrix2=tf.constant([[2],
                     [2]])

product=tf.matmul(matrix1,matrix2)

# method 1
# sess = tf.Session()
# result = sess.run(product)
# print(result)
# sess.close()

# method 2
with tf.Session() as sess:
    result2 = sess.run(product)
    print(result2)

结果

[[12]]

4.variable

import tensorflow as tf

state = tf.Variable(0,name='counter')
#print(state.name)
one=tf.constant(1)

new_value=tf.add(state,one)
update=tf.assign(state,new_value)

init=tf.initialize_all_variables() #must have if define variable

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

结果

1
2
3

5.placeholder

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.]}))   #feed_dict和placeholder是绑定的