TensorFlow学习（6）手写数字识别优化

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)

# 不是一张张图片放入神经网络，定义一个批次，一次 100
batch_size = 100
# 计算一个有多少批次，整除
n_batch = mnist.train.num_examples // batch_size

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

# 设置有百分之多少的神经元工作
keep_prob = tf.placeholder(tf.float32)

# 学习率
lr = tf.Variable(0.001, dtype=tf.float32)

# 创建一个简单的神经网络
# W = tf.Variable(tf.zeros([784, 10]))
# b = tf.Variable(tf.zeros([10]))

# 用截断的正太分布，标准差为 0.1 进行初始化
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 是某一层的神经元输出，keep_prob 设置有百分之多少的神经元工作
L1_dropout = tf.nn.dropout(L1, keep_prob)

# 增加2个隐藏层
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_dropout, W2)+b2)
L2_dropout = 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_dropout,W3)+b3)

# 交叉熵代价函数与 softmax 配合
# 因为 prediction 是通过 softmax 来的，它是类别概率数组，所以不能直接用普通的交叉熵函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))

# Adam
train_step = tf.train.AdamOptimizer(lr).minimize(loss)

init = tf.global_variables_initializer()

# 结果存放在布尔型列表中
# tf.equal 相等返回 True，否则 False，argmax 比较 y 中哪个元素的值为 1，返回该元素下标
correct_predition = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))
# 求准确率
# tf.cast 将布尔型转换为32位浮点型，True -> 1.0，False -> 0.0，然后求平均值，如有 9 个 1,1 个 0，平均值为 0.9，准确率为 0.9
accuracy = tf.reduce_mean(tf.cast(correct_predition, tf.float32))

with tf.Session() as sess:
    sess.run(init)
    # 循环 51 个周期，每个周期批次为 100，每个周期将所有图片都训练一次
    for epoch in range(51):
        # 随迭代周期降低学习率
        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})
        #训练完一个周期看下准确率
        test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images,y:mnist.test.labels, keep_prob: 1.0})
        train_acc = sess.run(accuracy, feed_dict={x:mnist.train.images,y:mnist.train.labels, keep_prob: 1.0})
        learning_rate = sess.run(lr)
        print('Iter ' + str(epoch) + ', Testing Accuracy' + str(test_acc) + ', learning rate'+ str(learning_rate))

最后结果为：Iter 50, Testing Accuracy0.9825, learning rate7.6944976e-05