MNIST手写识别(二)
通过TensorFlow实现多层感知机,识别MNIST数据集,最终正确率98%左右。
## 通过TensorFlow实现多层感知机,识别MNIST数据集
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()
# 给隐含层参数设置Variable并初始化
in_units = 784 #输入节点数
h1_units = 300 #隐含层输出节点数(此模型中200-1000区别都不大)
W1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev=0.1)) #权重初始化为标准差为0.1的截断的正态分布
b1 = tf.Variable(tf.zeros([h1_units])) #偏置初始化为0
W2 = tf.Variable(tf.zeros([h1_units, 10]))
b2 = tf.Variable(tf.zeros([10]))
# 定义输入x的placeholder
x = tf.placeholder(tf.float32, [None, in_units])
keep_prob = tf.placeholder(tf.float32) #keep_prob通常训练时小于1,测试时等于1
# 定义模型结构,首先定义隐含层
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)
# 定义损失函数cross_entropy
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),reduction_indices=[1]))
# 优化器选择自适应优化器Adagrad
train_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)
# 训练模型
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})
# 对准确率进行验证
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}))