教程鏈接:面向機器學習專家的 MNIST 高級教程
利用CNN卷積神經網絡訓練MNIST手寫字體,mnist手寫字體素材爲28*28像素的圖片,本程序中採用兩層卷積神經網絡與密集連接層,利用ReLU激活函數與Adam梯度最速下降方法進行訓練
代碼如下:
#下載引入數據集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf
#設置默認會話(session)
sess = tf.InteractiveSession()
#設置模型變量
x = tf.placeholder(tf.float32, [None, 784])
#W = tf.Variable(tf.zeros([784, 10]))
#b = tf.Variable(tf.zeros([10]))
#y = tf.nn.softmax(tf.matmul(x, W) + b)
#權重初始化
def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
#卷積與池化
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#構建模型
#第一層卷積
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#第二層卷積
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#密集連接層
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#Dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#輸出層
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
#訓練模型
#成本函數:交叉熵
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#評估模型
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
#初始化變量#啓動圖(graph)
sess.run(tf.initialize_all_variables())
#訓練
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict = {x:batch[0],y_:batch[1],keep_prob:0.5})
print("test accuracy %g"%accuracy.eval(feed_dict = {x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))
運行結果: