Tensorflow1学习-2 mnist手写数字识别率提升到98%

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

#超参数
lr = tf.Variable(0.001, dtype=tf.float32)
drop_out = 1.0

#载入数据
mnist = input_data.read_data_sets('./MNIST_data', one_hot=True)

#每个批次的大小
batch_size = 50
#计算一共多少个批次
n_batch = mnist.train.num_examples // batch_size

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

#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
B1 = tf.Variable(tf.zeros([500])+0.1)
L1 = tf.nn.tanh(tf.matmul(x, W1) + B1)
L1_drop = tf.nn.dropout(L1, keep_prob)

W2 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1))
B2 = tf.Variable(tf.zeros([300])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop, W2) + B2)
L2_drop = tf.nn.dropout(L2, keep_prob)

W3 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1))
B3 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop, W3) + B3)

#交叉熵代价函数
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
#使用adam优化器
train_step = tf.train.AdamOptimizer(lr).minimize(cost)

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

#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))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(51):
        sess.run(tf.assign(lr, 0.001*(0.95 ** epoch)))
        for batch in range(n_batch):
            batchx, batchy = mnist.train.next_batch(batch_size)
            sess.run(train_step, feed_dict={x:batchx, y:batchy, keep_prob:drop_out})

        Learning_rate = sess.run(lr)
        test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:drop_out})
        train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels, keep_prob: drop_out})
        print('Iter' + str(epoch) + ', Learning rate ' + str(Learning_rate) + ', Testing Accuracy ' + str(test_acc) + ', Trainging Accuracy ' + str(train_acc))

交叉熵损失函数 tf.nn.softmax_cross_entropy_with_logits()
dropout 防止过拟合
动态调整学习率
优化器