TensorFlow编程模型和MNIST简单实现

1、TensorFlow 编程模型

    TensorFlow 编程模型由会话session构成，一个会话中可以有多个有向图graph。图中包括节点node和连接节点的边edge。数据以张量tensor的形式在边中流动形成数据流flow。

import tensorflow as tf
#初始化权重和偏向
w = tf.Variable(tf.zeros([data_shape]))
b = tf.Variable(tf.zeros([data_shape]))
#输入数据
x = tf.placeholder(data_tpye,d ata_shape)
#定义激活函数
relu = tf.nn.relu(rf.matmul(x,w)+b)
#定义代价函数
cost = [...]
#定义会话
sess = tf.Session()
#获取batch进行迭代
for step in range(0,10):
  input = [...]
  result = sess.run(cost,feed_dict={x:input})
  print(step,result) 

2、MNIST简单实现

    TensorFlow简单实现手写数字识别

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据
mnist = input_data.read_data_sets("MNIST_sata",one_hot=True)
#每个批次的大小
batch_size = 100
#计算一共有多少批次
n_batch = mnist.train.num_examples
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
#创建一个简单的神经网络
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,W)+b)
#定义代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
#使用梯度下降法
optimizer = tf.train.GradientDescentOptimizer(0.2)
train_step = optimizer.minimize(loss)
#求准确率
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        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})
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc)