TensorFlow编程入门-优快云博客

本文介绍TensorFlow的基础操作，包括计算图、会话管理和基本运算，演示变量使用、线性回归和手写数字识别等实例，适合初学者快速上手。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

一句话概述

Tensorflow是一个通过计算图的形式来表述计算的编程系统，计算图也叫数据流图，可以把计算图看做是一种有向图，Tensorflow中的每一个计算都是计算图上的一个节点，而节点之间的边描述了计算之间的依赖关系。

1、创建会话，执行会话

import tensorflow as tf
#创建一个常量op
m1 = tf.constant([[3,3]])
m2 = tf.constant([[2],[3]])
#创建一个矩阵乘法op,把m1和m2传入
product = tf.matmul(m1,m2)
print(product)
#定义一个会话，启动默认图
sess = tf.Session()
#调用sess的run方法来执行矩阵乘法op
#run(product)触发了图中三个op
result = sess.run(product)
print(result)
sess.close()
#另一种形式
with tf.Session() as sess:
    result = sess.run(product)
    print(result)

2、变量

x = tf.Variable([1,2])
a = tf.constant([3,3])
#增加一个减法op
sub = tf.subtract(x,a)
#增加一个加法op
add = tf.add(x,sub)
#初始化变量
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(sub))
    print(sess.run(add))

#创建一个变量初始化为0
state = tf.Variable(0,name='counter')
#创建一个op，作用是使state+1
new_value = tf.add(state,1)
#赋值op
update = tf.assign(state,new_value)
#变量初始化
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(state))
    for _ in range(5):
        print(sess.run(update))

3、简单实例

#使用numpy生成100个随机点
x_data = np.random.rand(100)
y_data = x_data * 0.1 + 0.2
#构建一个线性模型
b = tf.Variable(0.)
k = tf.Variable(0.)
y = k * x_data + b
#二次代价函数
loss = tf.reduce_mean(tf.square(y_data-y))
#定义一个梯度下降法来进行训练的优化器
optimizer = tf.train.GradientDescentOptimizer(0.2)
train = optimizer.minimize(loss)
#初始化变量
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for step in range(201):
        sess.run(train)
        if step % 20 == 0:
            print(step,sess.run([k,b]))

4、线性回归

#一个例子
#使用numpy生成200个随机点
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data) + noise

#定义两个placeholder
x = tf.compat.v1.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

#定义神经网络中间层
Weights_L1 = tf.Variable(tf.random.normal([1,10]))
biases_L1 = tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weights_L1)+biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)

#定义神经网络输出层
Weights_L2 = tf.Variable(tf.random_normal([10,1]))
biases_L2 = tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)
#二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
#使用梯度下降法训练
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train_step,feed_dict={x:x_data,y:y_data})
    prediction_value = sess.run(prediction,feed_dict = {x: x_data})
    #画图
    plt.figure()
    plt.scatter(x_data,y_data)
    plt.plot(x_data,prediction_value,'r-',lw=5)
    plt.show()

5、手写数字识别

#手写数字识别
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot = True)
#每个批次大小
batch_size = 100
#计算一共需要多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
lr = tf.Variable(0.001,dtype=tf.float32)
#创建一个简单的神经网络
W = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
b = tf.Variable(tf.zeros([500])+0.1)
l = tf.nn.tanh(tf.matmul(x,W)+b)
l_drop = tf.nn.dropout(l,keep_prob)

w1 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1))
b1 = tf.Variable(tf.zeros([300])+0.1)
l1 = tf.nn.tanh(tf.matmul(l_drop,w1)+b1)
l2_drop = tf.nn.dropout(l1,keep_prob)

w2 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1))
b2 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(l2_drop,w2)+b2)
#二次代价函数
# loss = tf.reduce_mean(tf.square(y-prediction))
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits = prediction))
#使用梯度下降法
# train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
train_step = tf.train.AdamOptimizer(lr).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存在一个bool列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(20):
        sess.run(tf.assign(lr,0.001*(0.95**epoch)))
        for batch in range(n_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x: batch_xs, y: batch_ys,keep_prob:1.0})
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images, y:mnist.test.labels,keep_prob:1.0})
        print("Iter" + str(epoch) + "Testing Accuracy" + str(acc))