使用TensorFlow实现多层感知机识别手写数字

这个例子仍旧是根据《TensorFlow 实战》一书中敲的，使用TensorFlow搭建简单的神经网络，进行手写数字的识别。这个神经网络只有一个隐藏层，隐藏层节点数为300。下面是代码。

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

#  载入数据集，下载到本地更方便使用
mnist = input_data.read_data_sets("F:/MNIST_data", one_hot=True)
sess = tf.InteractiveSession()

#  784为手写数字图片28*28个像素展开为一维向量的大小，就是784
#  设置只有一个隐藏层，节点数为300，最后的输出为10，即0-9个数字的分类结果
in_units = 784
h1_units = 300
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]))

x = tf.placeholder(tf.float32, [None, in_units])
keep_prob = tf.placeholder(tf.float32)

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)

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 i in range(3000):
    batch_x, bath_y = mnist.train.next_batch(100)
    train_step.run({x: batch_x, y_: bath_y, keep_prob: 0.75})

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