# 训练cifar10的简单例子

cifar10的数据最好自己先下载好

import cifar10,cifar10_input
import tensorflow as tf
import numpy as np
import time

#max_steps = 30000
max_steps = 1000
data_dir = 'cifar-10-batches-bin'
batch_size = 128

# 配置每个 GPU 上占用的内存的比例
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))

loss采用L2正则化，所以所有需要加入L2的都要使用variable_with_weight_loss函数来定义，这样自动加入losses中

def variable_with_weight_loss(shape, stddev, wl):
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
if wl is not None:
weight_loss = tf.multiply(tf.nn.l2_loss(var), wl, name='weight_loss')
return var

def loss(logits, labels):
#      """Add L2Loss to all the trainable variables.
#      Add summary for "Loss" and "Loss/avg".
#      Args:
#        logits: Logits from inference().
#        labels: Labels from distorted_inputs or inputs(). 1-D tensor
#                of shape [batch_size]
#      Returns:
#        Loss tensor of type float.
#      """
#      # Calculate the average cross entropy loss across the batch.
labels = tf.cast(labels, tf.int64)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=logits, labels=labels, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')

# The total loss is defined as the cross entropy loss plus all of the weight
# decay terms (L2 loss).

###

#cifar10.maybe_download_and_extract()

train和test集使用了现成库做了封装

images_train, labels_train = cifar10_input.distorted_inputs(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)   

image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])

#logits = inference(image_holder)

weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=0.0)
kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME')
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
#norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
norm1 = pool1

weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64], stddev=5e-2, wl=0.0)
kernel2 = tf.nn.conv2d(norm1, weight2, [1, 1, 1, 1], padding='SAME')
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))
#norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
norm2 = conv2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],

reshape = tf.reshape(pool2, [batch_size, -1])
dim = reshape.get_shape()[1].value
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, wl=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3)

weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, wl=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)

weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/192.0, wl=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))

loss = loss(logits, label_holder)

top_k_op = tf.nn.in_top_k(logits, label_holder, 1)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

tf.train.start_queue_runners()

start_time1 = time.time()
for step in range(max_steps):
start_time = time.time()
image_batch,label_batch = sess.run([images_train,labels_train])
_, loss_value = sess.run([train_op, loss],feed_dict={image_holder: image_batch,
label_holder:label_batch})
duration = time.time() - start_time

if step % 10 == 0:
examples_per_sec = batch_size / duration
sec_per_batch = float(duration)

format_str = ('step %d, loss = %.2f (%.1f examples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, examples_per_sec, sec_per_batch))

duration1 = time.time() - start_time1
print("Use time = "+ str(duration1))

num_examples = 10000
import math
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0
total_sample_count = num_iter * batch_size
step = 0
while step < num_iter:
image_batch,label_batch = sess.run([images_test,labels_test])
predictions = sess.run([top_k_op],feed_dict={image_holder: image_batch,
label_holder:label_batch})
true_count += np.sum(predictions)
step += 1

precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)

• 广告
• 抄袭
• 版权
• 政治
• 色情
• 无意义
• 其他

120