Tensorflow实现CIFAR-10分类问题-详解四cifar10_eval.py

最后我们采用cifar10_eval.py文件来评估以下训练模型在保留(hold-out samples)样本下的表现力，其中保留样本的容量为10000。为了验证模型在训练过程中的表现能力的变化情况，我们验证了最近一些训练过程中产生的checkpoint files。

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

parser = cifar10.parser

parser.add_argument('--eval_dir', type=str, default='/home/liu/NewDisk/LearnTensor/cifar10_eval',
                    help='Directory where to write event logs.')

parser.add_argument('--eval_data', type=str, default='test',
                    help='Either `test` or `train_eval`.')

parser.add_argument('--checkpoint_dir', type=str, default='/home/liu/NewDisk/LearnTensor/cifar10_train',
                    help='Directory where to read model checkpoints.')

parser.add_argument('--eval_interval_secs', type=int, default=60*5,
                    help='How often to run the eval.')#设置每隔多长时间做一侧评估

parser.add_argument('--num_examples', type=int, default=10000,
                    help='Number of examples to run.')

parser.add_argument('--run_once', type=bool, default=False,
                    help='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.# 启动很多线程，并把coordinator传递给每一个线程
    coord = tf.train.Coordinator()
    try:
      threads = []#使用coord统一管理所有线程
      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])#计算num_iter个评估用例是否预测正确，应该到不了num_iter就会满足coord.should_shop()然后退出
        true_count += np.sum(predictions)#累加
        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)# 读入评估图片和标签

    # 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) #判定predictions的top k个预测结果是否包含targets，返回bool变量

    # Restore the moving average version of the learned variables for eval.
    variable_averages = tf.train.ExponentialMovingAverage(
        cifar10.MOVING_AVERAGE_DECAY)#创建计算均值的对象
    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()
    # 创建一个event file,用于之后写summary对象到FLAGS.eval_dir目录下的文件中
    summary_writer = tf.summary.FileWriter(FLAGS.eval_dir, g)
    # 每隔一定时间进行评估，只对当前训练好的最新的模型进行评估。
    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__':
  FLAGS = parser.parse_args()
  tf.app.run()

使用tensorboard实现变量的可视化，具体操作：
打开终端，输入

source activate tensorflow
tensorboard –logdir /your_path/cifar10_train/

打开相应网址即可…