tensorflow学习笔记——MNIST数据集分类

首先在这个网站下载MNIST数据集。下载后的数据如图所示：

压缩包不需要解压，直接使用。里面是二进制文件，因为用二进制文件训练网络比较快。

代码如下：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#载入数据
mnist = input_data.read_data_sets("E:/mnist",one_hot=True)

#每个批次大小
batch_size = 200

#计算一共有多少个批次
n_batch = mnist.train.num_examples//batch_size #整除

x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])

#网络有两个隐藏层，第一个隐藏层有700个节点，第二个隐藏层有100个节点
#W = tf.Variable(tf.zeros([784,10]))#只有第一层W可以初始化为0
W1 = tf.Variable(tf.truncated_normal([784,700],stddev=0.1))#一般使用截断正态分布初始化W
b1 = tf.Variable(tf.zeros([700]))
L1 = tf.matmul(x,W1) + b1
L1 = tf.nn.tanh(L1)
L1_drop = tf.nn.dropout(L1,keep_prob)

W2 = tf.Variable(tf.truncated_normal([700,100],stddev=0.1))
b2 = tf.Variable(tf.zeros([100]))
L2 = tf.matmul(L1_drop,W2) + b2
L2 = tf.nn.tanh(L2)

W3 = tf.Variable(tf.truncated_normal([100,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(L2,W3)+b3)
drop_L = tf.nn.dropout(prediction,keep_prob)#这里定义了dropout，不过使用效果没有不使用好所以后面并没有使用

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=prediction))

#梯度下降法训练
# train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
train_step = tf.train.AdamOptimizer(0.8e-4).minimize(loss)
#使用Adam时，小的学习率适合批次数量较小的情况，大的学习率适合批次数量较大的情况，大家可以自己改一下试试
# train_step = tf.train.AdadeltaOptimizer(0.1).minimize(loss)
# train_step = tf.train.MomentumOptimizer(0.1,0.9,use_nesterov=True).minimize(loss)
# train_step = tf.train.AdagradOptimizer(0.1).minimize(loss)
# train_step = tf.train.RMSPropOptimizer(0.01).minimize(loss)

init = tf.global_variables_initializer()

#求准确率
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)) #将布尔型转换为浮点型

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(100):
        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})#keep_prob设为1就是不使用dropout

        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1})
        print("Iter " + str(epoch) + " Accuracy:" + str(acc))

 结果如下：