Tensorflow_MNIST数据集上结果改进

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/lansetiankong2104/article/details/79974284
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#导入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
batch_size = 100
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)
lr = tf.Variable(0.001, dtype=tf.float32)

#构造神经网络
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)

#定义损失函数和训练的优化器
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
train_step = tf.train.AdamOptimizer(lr).minimize(loss)

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

#计算准确率
correction_prediction = tf.equal(tf.argmax(y,1), tf.argmax(prediction,1))
accuracy = tf.reduce_mean(tf.cast(correction_prediction, tf.float32))

#创建会话,分批迭代训练,每次迭代调整lr,并计算识别准确率
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):
            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})
            
        learning_rate = sess.run(lr)
        acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})
        print("Iter " + str(epoch) + ", Testing Accuracy " + str(acc) + ", Learing Rate " + str(learning_rate))

Iter 50, Testing Accuracy 0.9815, Learing Rate 7.6944976e-05

结果有待进一步改进。。。。

阅读更多

没有更多推荐了,返回首页