tesorflow 实现多层感知器（MLP）（亦即全连接网）

来自＜ｔｅｎｓｏｒｆｌｏｗ实战＞一书

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)
sess = tf.InteractiveSession()   # 默认的　之后各项操作就不用指定ｓｅｓｓｉｏｎ了
# 参数初始化
in_units = 784   # 输入
h1_units = 300   # 输出
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]))
# 定义placeholder
x = tf.placeholder(tf.float32,[None, in_units])
keep_prob = tf.placeholder(tf.float32)  # dropout的比率也作为一个输入
# 定义模型结构
hidden1 = tf.nn.relu(tf.matmul(x, W1) + b1)  # relu隐含层
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)  # dropout层
y = tf.nn.softmax(tf.matmul(hidden1_drop, W2) + b2)   # 输出


# 定义损失函数和选择优化器

y_ = tf.placeholder(tf.float32, [None, 10])  # 标签
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)


# 训练
tf.global_variables_initializer().run()
for i in range(3000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    train_step.run({x: batch_xs, y_: batch_ys, keep_prob: 0.75})

# 对模型进行准确率评测
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(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}))