mnist——多层感知机

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("MNIST_data/", one_hot=True)
sess=tf.InteractiveSession()
in_units=784
h1_units=300
x=tf.placeholder(tf.float32, [None, in_units])
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]))

                       //w3=tf.Variable(tf.truncated_normal([h1_units, h1_units], stddev=0.1))
                       //b3=tf.Variable(tf.zeros([h1_units]))
keep_prob=tf.placeholder(tf.float32)
hidden1=tf.nn.relu(tf.matmul(x,w1)+b1)
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)          //随机讲一部分节点设为0，keep_prob参数为保留数据而不置0的比例
                                   //hidden2=tf.nn.relu(tf.matmul(hidden1_drop, w3)+ b3)
                                    //hidden2_drop = tf.nn.dropout(hidden2, keep_prob)
                                      //y=tf.nn.softmax(tf.matmul(hidden2_drop,w2)+b2)   多加一层；
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(0.2).minimize(cross_entropy)               //当多加一层时，学习率在0.2的时候能达到0.98的准确率，但是在0.3的学习率时只有0.098的准确率
tf.global_variables_initializer().run()
for i in range(1000):
    batch_xs, batch_ys=mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x:batch_xs, y_:batch_ys, keep_prob: 0.5})
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}))         //训练时为防止过拟合<1，测试时为1

 

转载于:https://www.cnblogs.com/Magina-learning/p/7908126.html