import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1)) # 1表示列,即求每行第几列为最大值
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy)
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1) # 产生截断正态分布随机数,取值范围为 [ mean - 2 * stddev, mean + 2 * stddev ]
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W): # 卷积层
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') # [batch, x_movement, y_movement, channels]
def max_pool_2x2(x): # 池化层
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # 池化窗口
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 28 * 28]) # 28×28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32) # 保持多少结果不被dropout掉
x_image = tf.reshape(xs, [-1, 28, 28, 1]) # 第一个参数表示导入多少个图片,-1表示先不管,自动计算。通道为1
print(x_image.shape) # [n_samples, 28, 28, 1]
# conv1 layer
W_conv1 = weight_variable([5, 5, 1, 32]) # [filter_height, filter_width, in_channels(1通道), out_channels(32个卷积核)]
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_2x2(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
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_2x2(h_conv2) # output size 7×7×64
# fc1 layer
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64]) # [n_samples, 7, 7, 64] ->> [n_samples, 7 * 7 * 64]
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# fc2 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)
# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) # loss
optimizer = tf.train.AdamOptimizer(1e-4)
train = optimizer.minimize(cross_entropy)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for steps in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if steps % 50 == 0:
print(compute_accuracy(mnist.test.images, mnist.test.labels))
Tensorflow学习--CNN(MNIST)
最新推荐文章于 2020-07-08 15:32:56 发布