TensorFlow实现多层感知机

多层感知机

• http://blog.csdn.net/qq_33096883/article/details/76408801

代码

#!/usr/bin/python3.5

import tensorflow as tf

import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

sess = tf.InteractiveSession()

# 输入节点数
in_units = 784
# 隐藏层的输出节点数
h1_units = 300

# 权重初始化为截断的正态分布，标准差为0.1
W1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev=0.1))
b1 = tf.Variable(tf.zeros([h1_units]))
W2 = tf.Variable(tf.zeros([h1_units, 10]))
b2 = tf.Variable(tf.zeros([10]))

# Dropout: 将网络的某一层的输出节点数据随机丢弃一部分
#          创造了很多新的随机样本，通过增大样本量，减少特征数量来防止过拟合
# keep_prob: 保留节点的概率,通常训练小于1，预测等于1
x = tf.placeholder(tf.float32, [None, in_units])    # None表示可以随意设置
keep_prob = tf.placeholder(tf.float32)

# 处理
hidden1 = tf.nn.relu(tf.matmul(x, W1) + b1)
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)
y = tf.nn.softmax(tf.matmul(hidden1_drop, W2) + b2)

# Adagrad: 优化SGD
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))

train_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

tf.global_variables_initializer().run()

for _ in range(3000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys, keep_prob : 0.75})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

运行结果

0.9779