简单分类模型，之后会加隐藏层

附一个论文https://arxiv.org/pdf/1207.0580.pdf

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

#每个批次的大小
batch_size = 100 #可修改
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])#可加隐藏层
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]))#可修改初始化函数W = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,W) + b)
#prediction = tf.nn.softmax(tf.matmul(x,W) + b)
#prediction = tf.nn.softplus(tf.matmul(x,W) + b)
#prediction = tf.nn.sigmoid(tf.matmul(x,W) + b)
#prediction = tf.nn.elu(tf.matmul(x,W) + b)
#prediction = tf.nn.relu(tf.matmul(x,W) + b)

#定义一个二次代价函数
# loss = tf.reduce_mean(tf.square(y-prediction))#改换交叉熵
#交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))#不求平均值难收敛
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)#可改学习率

#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个bool型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax()返回一维张量中最大的值所在的位置
#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(21):#可修改迭代次数
        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 Accurary " + str(acc))#记住整型不可直接print加上str()转换

在这里插入代码片