《深度学习之Tensorflow》学习笔记九

建立一个简单的卷积神经网络：

import cifar10_input
import tensorflow as tf
import numpy as np

#每次导入28张图片进行计算
batch_size = 28
# 注意数据集存放的路径
data_dir = r'D:\anaconda\a_lianxi\cifar_study\tmp\cifar10_data\cifar-10-batches-bin'
print('begin')
images_train,labels_train = cifar10_input.inputs(eval_data=False,data_dir=data_dir,batch_size=batch_size)
images_test,labels_test = cifar10_input.inputs(eval_data=True,data_dir=data_dir,batch_size=batch_size)
print('begin data')

def weight_variable(shape):
    return tf.Variable(tf.truncated_normal(shape, stddev=0.1))

def bias_variable(shape):
    return tf.Variable(0.1,shape=shape)

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')

def avg_pool_6x6(x):
    return tf.nn.max_pool(x,ksize=[1,6,6,1],
                          strides=[1,6,6,1],padding='SAME')

x = tf.placeholder(tf.float32,[None,24,24,3])
y = tf.placeholder(tf.float32,[None,10])

# 构建网络
x_image = tf.reshape(x,[-1,24,24,3])

#第一层卷积
W_conv1 = weight_variable([5,5,3,64])
b_conv1 = bias_variable([64])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#第二层卷积
W_conv2 = weight_variable([5,5,64,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#第三层卷积
W_conv3 = weight_variable([5,5,64,10])
b_conv3 = bias_variable([10])
h_conv3 = tf.nn.relu(conv2d(h_pool2,W_conv3) + b_conv3)

#第四层全局平均池化（相比传统的全连接层，效果更好。）
nt_hpool3 = avg_pool_6x6(h_conv3)
nt_hpool3_flat = tf.reshape(nt_hpool3,[-1,10])
y_conv = tf.nn.softmax(nt_hpool3_flat)

cross_entropy = -tf.reduce_sum(y*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(0.0001).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))

sess = tf.Session()
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)

for i in range(15000):
    image_batch,label_batch = sess.run([images_train,labels_train])
    label_b = np.eye(10)[label_batch]

    train_step.run({x:image_batch,y:label_b},session=sess)

    if i%200 == 0:
        train_accuracy = accuracy.eval({x:image_batch,y:label_b},session=sess)
        print("step %d, training accuracy %g"%(i,train_accuracy))

image_batch,label_batch = sess.run([image_test, label_test])
label_b = np.eye(10)[label_batch]
print('finished! test accuracy %g'%accuracy.eval({x:image_batch,y:label_b},session=sess))

下面开始学习深度学习的模型训练技巧。