import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
#定义计算准确率的函数
def compute_accuracy(v_xs,v_ys):
global prediction
y_pre = sess.run(prediction,feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
correct_prediction = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
result = sess.run(accuracy,feed_dict={xs:v_xs,ys:v_ys,keep_prob:1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape=shape,stddev=0.1)
#生成一个形状为shape,标准差为0.1的tensor
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1,shape=shape)
return tf.Variable(initial)
def conv2d(x,W):
#stride[1,x_movement,y_movement,1]
#must have stride[0]=stride[3]=1
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2d(x):
#ksize is same as strides
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#define placeholder for inputs to network
xs = tf.placeholder(tf.float32,[None,784])#28*28
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs,[-1,28,28,1])#这里的-1表示数量未知
#print(x_image.shape) the result will be [n_samples,28,28,1]
#conv1 layer
W_conv1 = weight_variable([5,5,1,32])#patch 5*5,in size 1,out size 32,过滤器大小为5*5,高度与图片一样是1,共32个过滤器
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)#output size 28*28*32
h_pool1 = max_pool_2d(h_conv1)#output size 14*14*32
#conv2 layer
W_conv2 = weight_variable([5,5,32,64])#patch 5*5,in size 32,out size 64,过滤器大小为5*5,高度与图片一样是32,共64个过滤器
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)#output size 14*14*64
h_pool2 = max_pool_2d(h_conv2)#output size 7*7*64
#func1 layer
W_fc1 =weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
#[n,sample,7,7,64]->>[n_samples,7*7*64]
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])#这里的-1是什么意思?-1是指先不管有多少个sample
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)#这里使用随机失活用来防止过拟合
#func2 layer
W_fc2 =weight_variable([1024,10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)
#train the neural network
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(0.0001).minimize(cross_entropy)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
for i in range(1000):
batch_xs,batch_ys = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys,keep_prob:0.5})
if i%50 == 0:
print(compute_accuracy(mnist.test.images,mnist.test.labels))
CNN的demo
最新推荐文章于 2023-05-14 17:29:07 发布