TensorFlow字体识别简单优化

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)
# 每个批次的大小
batch_size = 100
# 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])
y = tf.placeholder(tf.float32,[None,10])
# 用来定义某一部分张量进行学习
keep_prob = tf.placeholder(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]))
# prediction = tf.nn.softmax(tf.matmul(x,W)+b)
# 初始化方式改变
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)
# 用来用一部分变量进行学习
L1_prob = tf.nn.dropout(L1,keep_prob)

# 增加中间层
W2 = tf.Variable(tf.truncated_normal([500,500],stddev = 0.1))
b2 = tf.Variable(tf.zeros([500])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1,W2)+b2)
L2_prob = tf.nn.dropout(L2,keep_prob)


W3 = tf.Variable(tf.truncated_normal([500,100],stddev = 0.1))
b3 = tf.Variable(tf.zeros([100])+0.1)
L3 = tf.nn.tanh(tf.matmul(L2,W3)+b3)
L3_prob = tf.nn.dropout(L3,keep_prob)

W4 = tf.Variable(tf.truncated_normal([100,10],stddev = 0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L3_prob,W4)+b4)

# 二次代价函数
# loss = tf.reduce_mean(tf.square(y-prediction))
# 使用交叉熵损失函数+softmax
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y,logits = prediction))

# 定义梯度下降函数
# train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
# 1e-3是学习率
train_step = tf.train.AdamOptimizer(1e-2)

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


# 结果存放在一个布尔类型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
# 求准确率
# 将bool类型的预测结果转换为数值类型
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):
        for batch in range(n_batch):
#             图片的数据保存在xs中，图片的标签保存在ys中
            batch_xs,batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.7})
            
        test_acc = sess.run(accuracy,feed_dict = {x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
        print("Iter" + str(epoch)+",Tesing accuracy" +str(acc))
    

趁热，刚敲出来的。。赶紧的。。可实现。。