CIFAR-10与ImageNet图像识别

2.1.2 下载CIFAR-10 数据

python cifar10_download.py

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""Builds the CIFAR-10 network.

Summary of available functions:

 # Compute input images and labels for training. If you would like to run
 # evaluations, use inputs() instead.
 inputs, labels = distorted_inputs()

 # Compute inference on the model inputs to make a prediction.
 predictions = inference(inputs)

 # Compute the total loss of the prediction with respect to the labels.
 loss = loss(predictions, labels)

 # Create a graph to run one step of training with respect to the loss.
 train_op = train(loss, global_step)
"""
# pylint: disable=missing-docstring
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 = 'http://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

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
    with tf.variable_scope('conv1') as scope:
        kernel = _variable_with_weight_decay('weights',
                                             shape=[5, 5, 3, 64],
                                             stddev=5e-2,
                                             wd=0.0)
        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)
        _activation_summary(conv1)

    # pool1
    pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                           padding='SAME', name='pool1')
    # norm1
    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=0.0)
        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
    with tf.variable_scope('local3') as scope:
        # Move everything into depth so we can perform a single matrix multiply.
        reshape = tf.reshape(pool2, [FLAGS.batch_size, -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))
        local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
        _activation_summary(local3)

    # local4
    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=0.0)
        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)
    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.
    Returns:
      train_op: op for training.
    """
    # Variables that affect learning rate.
    num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size
    decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)

    # Decay the learning rate exponentially based on the number of steps.
    lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE,
                                    global_step,
                                    decay_steps,
                                    LEARNING_RATE_DECAY_FACTOR,
                                    staircase=True)
    tf.summary.scalar('learning_rate', lr)

    # Generate moving averages of all losses and associated summaries.
    loss_averages_op = _add_loss_summaries(total_loss)

    # Compute gradients.
    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)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())

    with tf.control_dependencies([apply_gradient_op, variables_averages_op]):
        train_op = tf.no_op(name='train')

    return train_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)

# 引入当前目录中的已经编写好的cifar10模块
import cifar10
import tensorflow as tf

# tf.app.flags.FLAGS是TensorFlow内部的一个全局变量存储器，同时可以用于命令行参数的处理
FLAGS = tf.app.flags.FLAGS

# 在cifar10模块中预先定义了f.app.flags.FLAGS.data_dir为CIFAR-10的数据路径，我们把这个路径改为cifar10_data
FLAGS.data_dir = 'cifar10_data/'

# 如果不存在数据文件，就会执行下载
cifar10.maybe_download_and_extract()

2.1.3 TensorFlow 的数据读取机制

实验脚本：

python test.py

import tensorflow as tf
import os
if not os.path.exists('read'):
    os.makedirs('read/')

# 新建一个Session
with tf.Session() as sess:
    # 我们要读三幅图片A.jpg, B.jpg, C.jpg
    filename = ['A.jpg', 'B.jpg', 'C.jpg']
    # string_input_producer会产生一个文件名队列
    filename_queue = tf.train.string_input_producer(filename, shuffle=False, num_epochs=5)
    # reader从文件名队列中读数据。对应的方法是reader.read
    reader = tf.WholeFileReader()
    key, value = reader.read(filename_queue)
    # tf.train.string_input_producer定义了一个epoch变量，要对它进行初始化
    tf.local_variables_initializer().run()
    # 使用start_queue_runners之后，才会开始填充队列
    threads = tf.train.start_queue_runners(sess=sess)
    i = 0
    while True:
        i += 1
        # 获取图片数据并保存
        image_data = sess.run(value)
        with open('read/test_%d.jpg' % i, 'wb') as f:
            f.write(image_data)
# 程序最后会抛出一个OutOfRangeError，这是epoch跑完，队列关闭的标志

2.1.4 实验：将CIFAR-10 数据集保存为图片形式

python cifar10_extract.py

# 导入当前目录的cifar10_input，这个模块负责读入cifar10数据
import cifar10_input
# 导入TensorFlow和其他一些可能用到的模块。
import tensorflow as tf
import os
import scipy.misc

def inputs_origin(data_dir):
    # filenames一共5个，从data_batch_1.bin到data_batch_5.bin
    # 读入的都是训练图像
    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包装成TensorFlow中queue的形式
    filename_queue = tf.train.string_input_producer(filenames)
    # cifar10_input.read_cifar10是事先写好的从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)
    # 将图片转换为实数形式
    reshaped_image = tf.cast(read_input.uint8image, tf.float32)
    # 返回的reshaped_image是一张图片的tensor
    # 我们应当这样理解reshaped_image：每次使用sess.run(reshaped_image)，就会取出一张图片
    return reshaped_image

if __name__ == '__main__':
    # 创建一个会话sess
    with tf.Session() as sess:
        # 调用inputs_origin。cifar10_data/cifar-10-batches-bin是我们下载的数据的文件夹位置
        reshaped_image = inputs_origin('cifar10_data/cifar-10-batches-bin')
        # 这一步start_queue_runner很重要。
        # 我们之前有filename_queue = tf.train.string_input_producer(filenames)
        # 这个queue必须通过start_queue_runners才能启动
        # 缺少start_queue_runners程序将不能执行
        threads = tf.train.start_queue_runners(sess=sess)
        # 变量初始化
        sess.run(tf.global_variables_initializer())
        # 创建文件夹cifar10_data/raw/
        if not os.path.exists('cifar10_data/raw/'):
            os.makedirs('cifar10_data/raw/')
        # 保存30张图片
        for i in range(30):
            # 每次sess.run(reshaped_image)，都会取出一张图片
            image_array = sess.run(reshaped_image)
            # 将图片保存
            scipy.misc.toimage(image_array).save('cifar10_data/raw/%d.jpg' % i)

2.2.3 训练模型

python cifar10_train.py --train_dir cifar10_train/ --data_dir cifar10_data/

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.")
tf.app.flags.DEFINE_integer('max_steps', 1000000, "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.")

def train():
    """
    Train CIFAR-10 for a number of steps.
    :return:
    """
    with tf.Graph().as_default():
        global_step = tf.contrib.framework.get_or_create_global_step()

        # Get images and labels for CIFAR-10.
        images, labels = cifar10.distorted_inputs()

        # Build a Graph that computes the logits predictions from the
        # inference model.
        logits = cifar10.inference(images)

        # 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)

        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
                    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))

        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()

2.2.4 在TensorFlow 中查看训练进度

tensorboard --logdir cifar10_train/

2.2.5 测试模型效果

python cifar10_eval.py --data_dir cifar10_data/ --eval_dir cifar10_eval/ --checkpoint_dir cifar10_train/

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()

使用TensorBoard查看性能验证情况：

tensorboard --logdir cifar10_eval/ --port 6007

拓展阅读

• 关于CIFAR-10 数据集， 读者可以访问它的官方网站https://www.cs.toronto.edu/~kriz/cifar.html 了解更多细节。此外， 网站 http://rodrigob.github.io/are_we_there_yet/build/classification_datasets_results.html#43494641522d3130 中收集了在CIFAR-10 数据集上表 现最好的若干模型，包括这些模型对应的论文。
• ImageNet 数据集上的表现较好的几个著名的模型是深度学习的基石， 值得仔细研读。建议先阅读下面几篇论文：ImageNet Classification with Deep Convolutional Neural Networks（AlexNet 的提出）、Very Deep Convolutional Networks for Large-Scale Image Recognition （VGGNet）、Going Deeper with Convolutions（GoogLeNet）、Deep Residual Learning for Image Recognition（ResNet）
• 在第2.1.3 节中，简要介绍了TensorFlow的一种数据读入机制。事实上，目前在TensorFlow 中读入数据大致有三种方法：（1）用占位符（即placeholder）读入，这种方法比较简单；（2）用队列的形式建立文件到Tensor的映射；（3）用Dataset API 读入数据，Dataset API 是TensorFlow 1.3 版本新引入的一种读取数据的机制，可以参考这 篇中文教程：https://zhuanlan.zhihu.com/p/30751039。