利用TensorFlow1.0搭建卷积神经网络用于识别MNIST数据集,算是深度学习里的hello world吧。虽然只有两个卷积层,但在训练集上的正确率已经基本达到100%了。
代码如下:
# Auther:Chaz
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()
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)
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')
x = tf.placeholder(tf.float32,[None,784])
y_ = tf.placeholder(tf.float32,[None,10])
x_image = tf.reshape(x,[-1,28,28,1])
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
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)
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)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
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)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y_conv),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
tf.initialize_all_variables().run()#tensorflow 1.0
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 ==0:
train_accuacy = accuracy.eval(feed_dict = {x:batch[0],y_:batch[1],keep_prob:1.0})
print("step %d,train accuarcy %g"%(i,train_accuacy))
train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
print("TEST ACCURACY %g" % accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))
训练一共训练了3个多小时,训练效果应当很棒。
但在测试集上,由于一次直接读入10000张图片,内存直接不够用,并没有测试出来。可以利用for循环分多次测试,求平均值。
据说,测试集识别率达到了98%。
还可以进行将训练结果进行保存,否则一次训练几个小时,时间也耗不起啊。