运行环境
win10, TensorFlow1.9.0（GPU版本），python3.6，编译器pycharm
文件说明
| 文件 | 用途 |
|---|---|
| cifar10_extrat.py | 从下载的原始数据读取数据集，并将他们保存为.jpg图片 |
| cifar10_download.py | 下载CIFAR-10数据集 |
| cifar10.py | 建立CIFAR-10预测模型 |
| cifar10_input.py | 在TensorFlow中读入CIFAR-10训练图片 |
| cifar10_train.py | 使用单个的CPU或者GPU进行训练 |
| cifar10_eval.py | 检测训练的准确率 |
代码及注释
cifar10_download.py完整代码及注释
import cifar10 #导入目录中已经有的cifar10模块
import tensorflow as tf
#tf.app.flags.FLAGS是tensorflow内部的一个全局变量存储器，同时可用于命令行参数的处理
FLAGS=tf.app.flags.FLAGS
#在cifar10模块已经预定义了tf.app.flags.FLAGS.data_dir为'/tmp/cifar10_data'（数据存放路径），
#这里把路径改为cifar10_data，如果没有此句，则是预定义的值；
FLAGS.data_dir='cifar10_data/'
#如果不存在这个文件，则执行下载，有的话，直接跳过；
cifar10.maybe_download_and_extract()
cifar10_extrat.py完整代码及注释
import tensorflow as tf
import os
import cifar10_input
import scipy.misc #注意scipy的版本，这里为1.2.1，之前用的高版本，有错；
import PIL
#
def inputs_origin(data_dir):
#os.path.join：连接两个或更多的路径名组件
filenames=[os.path.join(data_dir,'data_batch_%d.bin' % i)
for i in range(1,6)]
#判断文件是否存在
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: '+ f)
#将文件名的list包装包装成Tensorflow中的queue的形式（创建了一个文件队列名）
#filenames是一个列表 ，包含data_batch_1.bin到……5.bin共5个文件名
filename_queue=tf.train.string_input_producer(filenames)
#事先写好的从queue中读取文件的函数
#返回的结果read_input的属性uint8image就是图像的Tensor
read_input=cifar10_input.read_cifar10(filename_queue)
#将图片转换为实数的形式
reshaped_image=tf.cast(read_input.uint8image,tf.float32)
#返回的结果reshaped_image是一张图片的tensor
#reshaped_image理解：每次使用sess,run(reshaped_image)，就会取出一张图片
return reshaped_image
if __name__=='__main__':
with tf.Session() as sess:
reshaped_image=inputs_origin('cifar10_data/cifar-10-batches-bin')
#tf.train.start_queue_runners 启动填充队列的线程
#之前调用的函数已经有filename_queue=tf.train.string_input_producer(filenames)
#这个queue必须通过start_queue_runners才能启动
#若缺少start_queue_runners，程序将不执行
thread=tf.train.start_queue_runners(sess=sess)
#变量初始化
sess.run(tf.global_variables_initializer())
#创建文件夹
if not os.path.exists('cifar10_data/raw/'):
os.makedirs('cifar10_data/raw/')
#保存30张图片，每一个循环都会取出一张图片，并将图片保存
for i in range(30):
image_array=sess.run(reshaped_image)
scipy.misc.toimage(image_array).save('cifar10_data/raw/%d.jpg' % i)
注：tensorflow读取CIFAR-10数据的步骤：
1.用tf.train.string_input_producer建立队列
2.通过reader.read读取数据
3.调用tf.train.start_queue_runners
4.通过sess.run()取出图片结果
cifar10_download.py代码及注释：
import cifar10 #导入目录中已经有的cifar10模块
import tensorflow as tf
#tf.app.flags.FLAGS是tensorflow内部的一个全局变量存储器，同时可用于命令行参数的处理
FLAGS=tf.app.flags.FLAGS
#在cifar10模块已经预定义了tf.app.flags.FLAGS.data_dir为'/tmp/cifar10_data'（数据存放路径），
#这里把路径改为cifar10_data，如果没有此句，则是预定义的值；
FLAGS.data_dir='cifar10_data/'
#如果不存在这个文件，则执行下载，有的话，直接跳过；
cifar10.maybe_download_and_extract()
cifar10.py代码及注释：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import re
import sys
import tarfile
from six.moves import urllib
import tensorflow as tf
import cifar10_input
FLAGS = tf.app.flags.FLAGS
# Basic model parameters.
tf.app.flags.DEFINE_integer('batch_size', 128,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('data_dir', '/tmp/cifar10_data',
"""Path to the CIFAR-10 data directory.""")
tf.app.flags.DEFINE_boolean('use_fp16', False,
"""Train the model using fp16.""")
# Global constants describing the CIFAR-10 data set.
IMAGE_SIZE = cifar10_input.IMAGE_SIZE
NUM_CLASSES = cifar10_input.NUM_CLASSES
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
# Constants describing the training process.
MOVING_AVERAGE_DECAY = 0.9999 # The decay to use for the moving average.
NUM_EPOCHS_PER_DECAY = 350.0 # Epochs after which learning rate decays.
LEARNING_RATE_DECAY_FACTOR = 0.1 # Learning rate decay factor.
INITIAL_LEARNING_RATE = 0.1 # Initial learning rate.
# If a model is trained with multiple GPUs, prefix all Op names with tower_name
# to differentiate the operations. Note that this prefix is removed from the
# names of the summaries when visualizing a model.
TOWER_NAME = 'tower'
DATA_URL = 'https://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
def _activation_summary(x):
"""Helper to create summaries for activations.
Creates a summary that provides a histogram of activations.
Creates a summary that measures the sparsity of activations.
Args:
x: Tensor
Returns:
nothing
"""
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
tf.summary.histogram(tensor_name + '/activations', x)
tf.summary.scalar(tensor_name + '/sparsity',
tf.nn.zero_fraction(x))
def _variable_on_cpu(name, shape, initializer):
"""Helper to create a Variable stored on CPU memory.
Args:
name: name of the variable
shape: list of ints
initializer: initializer for Variable
Returns:
Variable Tensor
"""
with tf.device('/cpu:0'):
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = tf.get_variable(name, shape, initializer=initializer, dtype=dtype)
return var
def _variable_with_weight_decay(name, shape, stddev, wd):
"""Helper to create an initialized Variable with weight decay.
Note that the Variable is initialized with a truncated normal distribution.
A weight decay is added only if one is specified.
Args:
name: name of the variable
shape: list of ints
stddev: standard deviation of a truncated Gaussian
wd: add L2Loss weight decay multiplied by this float. If None, weight
decay is not added for this Variable.
Returns:
Variable Tensor
"""
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = _variable_on_cpu(
name,
shape,
tf.truncated_normal_initializer(stddev=stddev, dtype=dtype))
if wd is not None:
weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
return var
def distorted_inputs():
"""Construct distorted input for CIFAR training using the Reader ops.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.distorted_inputs(data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inputs(eval_data):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.inputs(eval_data=eval_data,
data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
#输入的参数为images，即图像的Tensor
#输出是图像属于各个类别的Logit
def inference(images):
"""Build the CIFAR-10 model.
Args:
images: Images returned from distorted_inputs() or inputs().
Returns:
Logits.
"""
# We instantiate all variables using tf.get_variable() instead of
# tf.Variable() in order to share variables across multiple GPU training runs.
# If we only ran this model on a single GPU, we could simplify this function
# by replacing all instances of tf.get_variable() with tf.Variable().
#
# conv1（建立第一个卷积层）
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 3, 64],
stddev=5e-2,
wd=None)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name=scope.name)
#summary是将输出写到tensorboard
_activation_summary(conv1)
# pool1(第一层卷积层的池化)
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding='SAME', name='pool1')
# norm1（这是局部响应归一化层，现在数模型大多不采用）
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 64, 64],
stddev=5e-2,
wd=None)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.1))
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv2)
# norm2
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm2')
# pool2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME', name='pool2')
# local3（全连接层1）
with tf.variable_scope('local3') as scope:
# Move everything into depth so we can perform a single matrix multiply.
#后面不做卷积了，所以把pool2进行reshape,方面做全连接
reshape = tf.reshape(pool2, [images.get_shape().as_list()[0], -1])
dim = reshape.get_shape()[1].value
weights = _variable_with_weight_decay('weights', shape=[dim, 384],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1))
#全连接。输出是relu(Wx+b)
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
_activation_summary(local3)
# local4(全连接层2)
with tf.variable_scope('local4') as scope:
weights = _variable_with_weight_decay('weights', shape=[384, 192],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
_activation_summary(local4)
# linear layer(WX + b),
# We don't apply softmax here because
# tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits
# and performs the softmax internally for efficiency.
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [192, NUM_CLASSES],
stddev=1/192.0, wd=None)
biases = _variable_on_cpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.0))
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear
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)
#交叉熵损失函数
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# The total loss is defined as the cross entropy loss plus all of the weight
# decay terms (L2 loss).
return tf.add_n(tf.get_collection('losses'), name='total_loss')
def _add_loss_summaries(total_loss):
"""Add summaries for losses in CIFAR-10 model.
Generates moving average for all losses and associated summaries for
visualizing the performance of the network.
Args:
total_loss: Total loss from loss().
Returns:
loss_averages_op: op for generating moving averages of losses.
"""
# Compute the moving average of all individual losses and the total loss.
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
losses = tf.get_collection('losses')
loss_averages_op = loss_averages.apply(losses + [total_loss])
# Attach a scalar summary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.summary.scalar(l.op.name + ' (raw)', l)
tf.summary.scalar(l.op.name, loss_averages.average(l))
return loss_averages_op
def train(total_loss, global_step):
"""Train CIFAR-10 model.
Create an optimizer and apply to all trainable variables. Add moving
average for all trainable variables.
Args:
total_loss: Total loss from loss().
global_step: Integer Variable counting the number of training steps processed. 计算训练步骤数的整数变量
Returns:
train_op: op for training.
"""
# Variables that affect learning rate. 影响学习率的变量
num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size #每一轮batch的次数（数据的总量/batch_size)
decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY) # n_batch*0.9999
#deacy_steps的理解：decay_steps为每隔这么多步，学习率就进行一次衰减，这里和n_batch_per_epoch差不多相等，即每进行n_batch_per_epoch，
#学习率衰减一次，可理解为每一轮，学习率衰减一次？？？
# Decay the learning rate exponentially based on the number of steps.
#指数衰减法
lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE, #0.1
global_step,
decay_steps,
LEARNING_RATE_DECAY_FACTOR,#0.1
staircase=True)
tf.summary.scalar('learning_rate', lr)
# Generate moving averages of all losses and associated summaries.#生成相关摘要用于可视化
loss_averages_op = _add_loss_summaries(total_loss)
# Compute gradients.计算梯度。这里为随机梯度下降法
with tf.control_dependencies([loss_averages_op]):
opt = tf.train.GradientDescentOptimizer(lr)
grads = opt.compute_gradients(total_loss)
# Apply gradients.
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
# Add histograms for trainable variables.
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name, var)
# Add histograms for gradients.
for grad, var in grads:
if grad is not None:
tf.summary.histogram(var.op.name + '/gradients', grad)
# Track the moving averages of all trainable variables.
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
with tf.control_dependencies([apply_gradient_op]):
variables_averages_op = variable_averages.apply(tf.trainable_variables())
return variables_averages_op
def maybe_download_and_extract():
"""Download and extract the tarball from Alex's website."""
dest_directory = FLAGS.data_dir
if not os.path.exists(dest_directory):
os.makedirs(dest_directory)
filename = DATA_URL.split('/')[-1]
filepath = os.path.join(dest_directory, filename)
if not os.path.exists(filepath):
def _progress(count, block_size, total_size):
sys.stdout.write('\r>> Downloading %s %.1f%%' % (filename,
float(count * block_size) / float(total_size) * 100.0))
sys.stdout.flush()
filepath, _ = urllib.request.urlretrieve(DATA_URL, filepath, _progress)
print()
statinfo = os.stat(filepath)
print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
extracted_dir_path = os.path.join(dest_directory, 'cifar-10-batches-bin')
if not os.path.exists(extracted_dir_path):
tarfile.open(filepath, 'r:gz').extractall(dest_directory)
cifar10_input.py代码及注释
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
# Process images of this size. Note that this differs from the original CIFAR
# image size of 32 x 32. If one alters this number, then the entire model
# architecture will change and any model would need to be retrained.
IMAGE_SIZE = 24
# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
#数据集中一个图片的字节数
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def _generate_image_and_label_batch(image, label, min_queue_examples,
batch_size, shuffle):
"""Construct a queued batch of images and labels.构建一批排队的图像和标签
Args:
image: 3-D Tensor of [height, width, 3] of type.float32.
label: 1-D Tensor of type.int32
min_queue_examples: int32, minimum number of samples to retain
in the queue that provides of batches of examples.
batch_size: Number of images per batch.
shuffle: boolean indicating whether to use a shuffling queue.
Returns:
images: Images. 4D tensor of [batch_size, height, width, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
# Create a queue that shuffles the examples, and then
# read 'batch_size' images + labels from the example queue.
num_preprocess_threads = 16
if shuffle:
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size,
min_after_dequeue=min_queue_examples)
else:
images, label_batch = tf.train.batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size)
# Display the training images in the visualizer.
tf.summary.image('images', images)
return images, tf.reshape(label_batch, [batch_size])
def distorted_inputs(data_dir, batch_size):
"""Construct distorted input for CIFAR training using the Reader ops.
Args:
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)] #把6个文件读取出来，
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.先创建一个文件名队列
filename_queue = tf.train.string_input_producer(filenames)
with tf.name_scope('data_augmentation'):
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for training the network. Note the many random
# distortions applied to the image.
# Randomly crop a [height, width] section of the image.（随机裁剪图片，从32*32裁剪到24*24）
distorted_image = tf.random_crop(reshaped_image, [height, width, 3])
# Randomly flip the image horizontally.（随机左右翻转图片）
distorted_image = tf.image.random_flip_left_right(distorted_image)
# Because these operations are not commutative, consider randomizing
# the order their operation.
# NOTE: since per_image_standardization zeros the mean and makes
# the stddev unit, this likely has no effect see tensorflow#1458.
#随机改变高度和对比度；
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)
# Subtract off the mean and divide by the variance of the pixels.剔除均值，并通过像素的方差除以。
float_image = tf.image.per_image_standardization(distorted_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.确保随机混洗具有良好的混合性能。
min_fraction_of_examples_in_queue = 0.4
#min_queue_examples=50000*0.4=20000
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)
print ('Filling queue with %d CIFAR images before starting to train. '
'This will take a few minutes.' % min_queue_examples)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=True) #返回的是特定格式的image和lable
def inputs(eval_data, data_dir, batch_size):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
if not eval_data:
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
else:
filenames = [os.path.join(data_dir, 'test_batch.bin')]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
with tf.name_scope('input'):
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
height, width)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(resized_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)
注：tensorflow中数据增强的实现代码片段在cifar10_input.py的distored_inputs()函数中。原始图片是reshaped_image，最后会得到一个数据增强后的训练样本distored_image。从reshaped_image到distored_inputs()的处理步骤如下：
1.对reshaped_image进行随机裁剪，从3232裁剪到2424进行训练。因为小块可以取在图像的任何位置，所以这一步可以大大增加训练集的样本数目。
2.对裁剪后的图片进行水平翻转，每张图片有50%的概率被翻转。
3.对得到的图片进行高度和对比度的随机改变。
训练时，直接使用distored_image进行训练即可。
cifar10_eval.py代码及注释
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import math
import time
import numpy as np
import tensorflow as tf
import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('eval_dir', '/tmp/cifar10_eval',
"""Directory where to write event logs.""")
tf.app.flags.DEFINE_string('eval_data', 'test',
"""Either 'test' or 'train_eval'.""")
tf.app.flags.DEFINE_string('checkpoint_dir', '/tmp/cifar10_train',
"""Directory where to read model checkpoints.""")
tf.app.flags.DEFINE_integer('eval_interval_secs', 60 * 5,
"""How often to run the eval.""")
tf.app.flags.DEFINE_integer('num_examples', 10000,
"""Number of examples to run.""")
tf.app.flags.DEFINE_boolean('run_once', False,
"""Whether to run eval only once.""")
def eval_once(saver, summary_writer, top_k_op, summary_op):
"""Run Eval once.
Args:
saver: Saver.
summary_writer: Summary writer.
top_k_op: Top K op.
summary_op: Summary op.
"""
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/cifar10_train/model.ckpt-0,
# extract global_step from it.
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
else:
print('No checkpoint file found')
return
# Start the queue runners.
coord = tf.train.Coordinator()
try:
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(qr.create_threads(sess, coord=coord, daemon=True,
start=True))
num_iter = int(math.ceil(FLAGS.num_examples / FLAGS.batch_size))
true_count = 0 # Counts the number of correct predictions.
total_sample_count = num_iter * FLAGS.batch_size
step = 0
while step < num_iter and not coord.should_stop():
predictions = sess.run([top_k_op])
true_count += np.sum(predictions)
step += 1
# Compute precision @ 1.
precision = true_count / total_sample_count
print('%s: precision @ 1 = %.3f' % (datetime.now(), precision))
summary = tf.Summary()
summary.ParseFromString(sess.run(summary_op))
summary.value.add(tag='Precision @ 1', simple_value=precision)
summary_writer.add_summary(summary, global_step)
except Exception as e: # pylint: disable=broad-except
coord.request_stop(e)
coord.request_stop()
coord.join(threads, stop_grace_period_secs=10)
def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
images, labels = cifar10.inputs(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
cifar10.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(FLAGS.eval_dir, g)
while True:
eval_once(saver, summary_writer, top_k_op, summary_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def main(argv=None): # pylint: disable=unused-argument
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.eval_dir):
tf.gfile.DeleteRecursively(FLAGS.eval_dir)
tf.gfile.MakeDirs(FLAGS.eval_dir)
evaluate()
if __name__ == '__main__':
tf.app.run()
cifar10_train.py代码及注释：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import time
import tensorflow as tf
import cifar10
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', '/tmp/cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")#日志文件存放地址
tf.app.flags.DEFINE_integer('max_steps', 1000,#100000
"""Number of batches to run.""")
tf.app.flags.DEFINE_boolean('log_device_placement', False,
"""Whether to log device placement.""")
tf.app.flags.DEFINE_integer('log_frequency', 10,
"""How often to log results to the console.""") #每隔这么多步，打印一次；
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():#生成默认图 generate default graph
global_step = tf.train.get_or_create_global_step()
# Get images and labels for CIFAR-10.
# Force input pipeline to CPU:0 to avoid operations sometimes ending up on
# GPU and resulting in a slow down.
with tf.device('/cpu:0'): #设置运行的设备
# 数据增强；两层调用，先调用cifar10.py中的，然后又调用cifar10_input中的
#最终返回值：Returns:
#images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
#labels: Labels. 1D tensor of [batch_size] size.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images) #返回的是属于各个类别的概率
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step) #学习率每一次变化，global_step每一次加一？？？
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time #两次运行的时间间隔；
self._start_time = current_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print (format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
# 管理分布式训练中一个重要方法，它相当于集成了一些监控训练组件。
# checkpoint_dir用于指定检查点保存的路径和文件名
#hooks：最重要的参数。它是一个SessionRunHook对象的列表，包含了所有希望外挂的组件
#config:session配置，是ConfigProtoproto格式
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()],
config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement)) as mon_sess:
while not mon_sess.should_stop():
mon_sess.run(train_op)
def main(argv=None): # pylint: disable=unused-argument
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.train_dir):
tf.gfile.DeleteRecursively(FLAGS.train_dir)
tf.gfile.MakeDirs(FLAGS.train_dir)
train()
if __name__ == '__main__':
tf.app.run()
Tensorboard及训练结果
要使用Tensorboard，先打开一个命令行窗口，输入以下命令：
tensorboard --logdir 日志信息存放的路径
运行cifar10_eval.py文件，准确率为86.3%
扫一扫
744
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
