tf实现多层感知机

tf实现多层感知机

使用数字数字集MNIST

# encoding：utf-8
# 多层感知机的tf实现
# author ： wht@92
from  tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf 

下载数据

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

设置参数

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]))

数据集格式展位

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

定义模型结构

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

定义损失函数和选择优化器

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)

训练步骤

tf.global_variables_initializer().run()
for i in range(300)：
    batch_xs, batch_ys = mnist.train.next_batch(100)    
    train_step.run({x:batch_xs, y_:batch_ys, keep_prod:0.75})

预测结果

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_prod:1.0}))