cifar10 卷积

import cifar10_input
import tensorflow as tf
import numpy as np

batch_size = 128
data_dir = '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 biase_variable(shape):
    return tf.Variable(tf.constant(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.avg_pool(x, ksize=[1, 6, 6, 1], strides=[1, 6, 6, 1], padding='SAME')


x = tf.placeholder(tf.float32, [None, 24, 24, 3])  # (?, 24, 24, 3)
y = tf.placeholder(tf.float32, [None, 10])  # Tensor("Placeholder_1:0", shape=(?, 10), dtype=float32)


W_conv1 = weight_variable([5, 5, 3, 64])
b_conv1 = biase_variable([64])

x_image = tf.reshape(x, [-1, 24, 24, 3])  # Tensor("Reshape_2:0", shape=(?, 24, 24, 3), dtype=float32)

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)  # (?, 24, 24, 64)
h_pool1 = max_pool_2x2(h_conv1)  # (?, 12, 12, 64)

W_conv2 = weight_variable([5, 5, 64, 64])
b_conv2 = biase_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_conv3 = weight_variable([5, 5, 64, 10])
b_conv3 = biase_variable([10])

h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)  # (?, 6, 6, 10)

nt_hpool3 = avg_pool_6x6(h_conv3)  # (?, 1, 1, 10)
nt_hpool3_flat = tf.reshape(nt_hpool3, [-1, 10])  # (?, 10)
y_conv = tf.nn.softmax(nt_hpool3_flat)  # (?, 10)

cross_entropy = -tf.reduce_sum(y * tf.log(y_conv))
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))

sess = tf.Session()
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
for i in range(10000):
    image_batch, label_batch = sess.run([images_train, labels_train])  # (128, 24, 24, 3) (128,)
    print(label_batch)
    label_b = np.eye(10, dtype=float)[label_batch]  # label_batch确定1的位置
    train_step.run(feed_dict={x: image_batch, y: label_b}, session=sess)
    if i % 200 == 0:
        train_accuracy = accuracy.eval(feed_dict={x: image_batch, y: label_b}, session=sess)
        print('step %d, training accuracy %g' % (i, train_accuracy))

print('finished! test accuracy %g' % accuracy.eval(feed_dict={x: image_batch, y: label_batch}, session=sess))
猜你喜欢
