tensorflow入门教程(三十四)疲劳检测之开眼闭眼识别

#
#作者：韦访
#博客：https://blog.csdn.net/rookie_wei
#微信：1007895847
#添加微信的备注一下是CSDN的
#欢迎大家一起学习
#

------韦访 20190118

1、概述

想用tensorflow做个疲劳检测，那么，该怎么下手呢？首先，根据常识，疲劳的时候，眼睛总会想闭上吧？还打哈欠吧？那么，先从眼睛入手，那么，要做的工作就是，首先得识别出眼睛的位置，也就是人脸关键点检测，在人脸识别上的教程（https://blog.csdn.net/rookie_wei/article/details/81676177）中，我们讲过，使用MTCNN可以将人脸检测出来，并且识别出5个关键点（左眼、右眼、鼻子、左嘴角、右嘴角）的位置。检测出眼睛的位置以后，就可以将眼睛的框出来，然后，识别它是开眼还是闭眼。打哈欠的话，是不是也得先识别嘴巴的位置啊？识别出嘴巴以后怎办，后面再说。这一讲，先来对眼睛的开闭进行识别。首先说明一下，我可能并不会给出一个完整的疲劳检测系统的教程，做出来了我可能也不会全部开源，仅供部分参考，作为之前教程的一个回顾，你懂的。

2、下载数据集

下载链接：

http://parnec.nuaa.edu.cn/xtan/data/datasets/dataset_B_Eye_Images.rar

数据集很小，2.5M而已。下载完以后，解压，得到目录如下：

根据文件夹名称，可以猜出应该是将眼睛分为4种状态了，分别是左眼开，左眼闭，右眼开，右眼闭。现在来看看每个文件夹里的内容是否跟我们预想的一样。

 

 

果然哈。那么接下来的问题就是，怎么识别？看过我tensorflow系列教程的朋友们应该知道，在第16讲和20讲中，我们使用过slim模型来进行图片分类，如果没看过，出门左转，链接如下：

16讲：https://blog.csdn.net/rookie_wei/article/details/80639490

20讲：https://blog.csdn.net/rookie_wei/article/details/80796009

这一讲，其实就是这两讲的一样应用，如果看过这两讲的朋友，就此打住，别往下看了，自己根据这两讲的内容做一下开闭眼的识别。

3、将数据集转成TFRecord格式

slim模型的下载、验证和结构我就不再重复讲了，现在，我们来将数据集转成TFRecord格式。我试过就按数据集的默认分类去识别，即左眼开，左眼闭，右眼开，右眼闭，效果并不好，识别的准确率仅为50%多一点，这肯定不行的。而我们现在的目的是，能识别出开眼和闭眼即可，所以并不需要分的那么详细。因此，现在将closedRightEyes文件夹下的所有图片剪切到closedLeftEyes文件夹，将openRightEyes文件夹下的所有图片剪切到openLeftEyes文件夹。再把两个空的文件夹删除，剩下的如下图所示，

将这个两个文件夹放到slim/images_data/eye_open_and_close文件夹下。

好了，接着就来修改代码了，仿造第20讲的教程做即可，写博客或者笔记的好处就是这样了，随手一拿就可以开干。首先，复制download_and_convert_flowers.py并将文件名改为convert_eye.py。修改后的源码如下，

# encoding:utf-8
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import math
import os
import random
import sys

import tensorflow as tf

from datasets import dataset_utils

# The URL where the Flowers data can be downloaded.
_DATA_URL = 'http://download.tensorflow.org/example_images/flower_photos.tgz'

# The number of images in the validation set.
_NUM_VALIDATION = 350

# Seed for repeatability.
_RANDOM_SEED = 0

# The number of shards per dataset split.
_NUM_SHARDS = 4


class ImageReader(object):
    """Helper class that provides TensorFlow image coding utilities."""

    def __init__(self):
        # Initializes function that decodes RGB JPEG data.
        self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
        self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)

    def read_image_dims(self, sess, image_data):
        image = self.decode_jpeg(sess, image_data)
        return image.shape[0], image.shape[1]

    def decode_jpeg(self, sess, image_data):
        image = sess.run(self._decode_jpeg,
                         feed_dict={self._decode_jpeg_data: image_data})
        assert len(image.shape) == 3
        assert image.shape[2] == 3
        return image


def _get_filenames_and_classes(dataset_dir):
    """Returns a list of filenames and inferred class names.
  Args:
    dataset_dir: A directory containing a set of subdirectories representing
      class names. Each subdirectory should contain PNG or JPG encoded images.
  Returns:
    A list of image file paths, relative to `dataset_dir` and the list of
    subdirectories, representing class names.
  """
    # 将flower_photos改为eye_photos
    flower_root = os.path.join(dataset_dir, 'eye_open_and_close')
    directories = []
    class_names = []
    for filename in os.listdir(flower_root):
        path = os.path.join(flower_root, filename)
        if os.path.isdir(path):
            directories.append(path)
            class_names.append(filename)

    photo_filenames = []
    for directory in directories:
        for filename in os.listdir(directory):
            path = os.path.join(directory, filename)
            photo_filenames.append(path)

    return photo_filenames, sorted(class_names)


def _get_dataset_filename(dataset_dir, split_name, shard_id):
    # 修改文件名，将flowersg改为eye
    output_filename = 'eye_%s_%05d-of-%05d.tfrecord' % (
        split_name, shard_id, _NUM_SHARDS)
    return os.path.join(dataset_dir, output_filename)


def _convert_dataset(split_name, filenames, class_names_to_ids, dataset_dir):
    """Converts the given filenames to a TFRecord dataset.
  Args:
    split_name: The name of the dataset, either 'train' or 'validation'.
    filenames: A list of absolute paths to png or jpg images.
    class_names_to_ids: A dictionary from class names (strings) to ids
      (integers).
    dataset_dir: The directory where the converted datasets are stored.
  """
    assert split_name in ['train', 'validation']

    num_per_shard = int(math.ceil(len(filenames) / float(_NUM_SHARDS)))

    with tf.Graph().as_default():
        image_reader = ImageReader()

        with tf.Session('') as sess:

            for shard_id in range(_NUM_SHARDS):
                output_filename = _get_dataset_filename(
                    dataset_dir, split_name, shard_id)

                with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:
                    start_ndx = shard_id * num_per_shard
                    end_ndx = min((shard_id + 1) * num_per_shard, len(filenames))
                    for i in range(start_ndx, end_ndx):
                        sys.stdout.write('\r>> Converting image %d/%d shard %d' % (
                            i + 1, len(filenames), shard_id))
                        sys.stdout.flush()

                        # Read the filename:
                        image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()
                        height, width = image_reader.read_image_dims(sess, image_data)

                        class_name = os.path.basename(os.path.dirname(filenames[i]))
                        class_id = class_names_to_ids[class_name]

                        example = dataset_utils.image_to_tfexample(
                            image_data, b'jpg', height, width, class_id)
                        tfrecord_writer.write(example.SerializeToString())

    sys.stdout.write('\n')
    sys.stdout.flush()


def _clean_up_temporary_files(dataset_dir):
    """Removes temporary files used to create the dataset.
  Args:
    dataset_dir: The directory where the temporary files are stored.
  """
    filename = _DATA_URL.split('/')[-1]
    filepath = os.path.join(dataset_dir, filename)
    tf.gfile.Remove(filepath)

    # 将flower_photos改为eye_photos
    tmp_dir = os.path.join(dataset_dir, 'eye_photos')
    tf.gfile.DeleteRecursively(tmp_dir)


def _dataset_exists(dataset_dir):
    for split_name in ['train', 'validation']:
        for shard_id in range(_NUM_SHARDS):
            output_filename = _get_dataset_filename(
                dataset_dir, split_name, shard_id)
            if not tf.gfile.Exists(output_filename):
                return False
    return True


def run(dataset_dir):
    """Runs the download and conversion operation.
  Args:
    dataset_dir: The dataset directory where the dataset is stored.
  """
    if not tf.gfile.Exists(dataset_dir):
        tf.gfile.MakeDirs(dataset_dir)

    if _dataset_exists(dataset_dir):
        print('Dataset files already exist. Exiting without re-creating them.')
        return

    # 因为我们不需要下载，所以这行注释掉
    # dataset_utils.download_and_uncompress_tarball(_DATA_URL, dataset_dir)
    photo_filenames, class_names = _get_filenames_and_classes(dataset_dir)
    class_names_to_ids = dict(zip(class_names, range(len(class_names))))

    # Divide into train and test:
    random.seed(_RANDOM_SEED)
    random.shuffle(photo_filenames)
    training_filenames = photo_filenames[_NUM_VALIDATION:]
    validation_filenames = photo_filenames[:_NUM_VALIDATION]

    # First, convert the training and validation sets.
    _convert_dataset('train', training_filenames, class_names_to_ids,
                     dataset_dir)
    _convert_dataset('validation', validation_filenames, class_names_to_ids,
                     dataset_dir)

    # Finally, write the labels file:
    labels_to_class_names = dict(zip(range(len(class_names)), class_names))
    dataset_utils.write_label_file(labels_to_class_names, dataset_dir)

    # 将这行注释掉，要不然转换完以后，原始数据会被删除
    # _clean_up_temporary_files(dataset_dir)
    print('\nFinished converting the Flowers dataset!')

再修改download_and_convert_data.py，添加

from datasets import convert_eye

再在

elif FLAGS.dataset_name == 'mnist':
  download_and_convert_mnist.run(FLAGS.dataset_dir)

后添加

elif FLAGS.dataset_name == 'eye':
  convert_eye.run(FLAGS.dataset_dir)

如下图所示，

然后运行命令，

python download_and_convert_data.py --dataset_name=eye --dataset_dir=images_data/eye_open_and_close

运行结果，

Instructions for updating:

Use tf.gfile.GFile.

>> Converting image 143/4498 shard 0Traceback (most recent call last):

  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1335, in _do_call

    return fn(*args)

  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1320, in _run_fn

    options, feed_dict, fetch_list, target_list, run_metadata)

  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1408, in _call_tf_sessionrun

    run_metadata)

tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected image (JPEG, PNG, or GIF), got unknown format starting with '\320\317\021\340\241\261\032\341\000\000\000\000\000\000\000\000'

 [[{{node DecodeJpeg}}]]

 

报错，看这句，

tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected image (JPEG, PNG, or GIF), got unknown format starting with

应该首先想到的是，我们数据集里是不是有不是图片的文件？

果然就看到了如下图这个文件，

删掉即可，注意，两个文件夹下都有这个文件啊。

再运行上面的命令，运行结果，

这就对了，当然，这个打印还是打印Flowsers数据集的，如果你有强迫症，也可以把它改了。去images_data/eye_open_and_close/文件夹下看看有没有TFRecord文件生成，

你也可以用第20讲的代码显示一张图片以验证这个TFRecord是否正确，我这里就不验证了。

4、定义datasets文件

继续修改代码，将datasets/flowers.py复制并重命名为eye.py ,将

_FILE_PATTERN = 'flowers_%s_*.tfrecord'

改为

_FILE_PATTERN = 'eye_%s_*.tfrecord'

将

SPLITS_TO_SIZES = {'train': 3320, 'validation': 350}

改为

SPLITS_TO_SIZES = {'train': 4496, 'validation': 350}

其中，train代表训练的图片张数，validation代表验证使用的图片张数。完整代码如下，

# Copyright 2016 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.
# ==============================================================================
"""Provides data for the flowers dataset.

The dataset scripts used to create the dataset can be found at:
tensorflow/models/research/slim/datasets/download_and_convert_flowers.py
"""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import tensorflow as tf

from datasets import dataset_utils

slim = tf.contrib.slim

_FILE_PATTERN = 'eye_%s_*.tfrecord'

SPLITS_TO_SIZES = {'train': 4496, 'validation': 350}

_NUM_CLASSES = 2

_ITEMS_TO_DESCRIPTIONS = {
    'image': 'A color image of varying size.',
    'label': 'A single integer between 0 and 4',
}


def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
  """Gets a dataset tuple with instructions for reading flowers.

  Args:
    split_name: A train/validation split name.
    dataset_dir: The base directory of the dataset sources.
    file_pattern: The file pattern to use when matching the dataset sources.
      It is assumed that the pattern contains a '%s' string so that the split
      name can be inserted.
    reader: The TensorFlow reader type.

  Returns:
    A `Dataset` namedtuple.

  Raises:
    ValueError: if `split_name` is not a valid train/validation split.
  """
  if split_name not in SPLITS_TO_SIZES:
    raise ValueError('split name %s was not recognized.' % split_name)

  if not file_pattern:
    file_pattern = _FILE_PATTERN
  file_pattern = os.path.join(dataset_dir, file_pattern % split_name)

  # Allowing None in the signature so that dataset_factory can use the default.
  if reader is None:
    reader = tf.TFRecordReader

  keys_to_features = {
      'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
      'image/format': tf.FixedLenFeature((), tf.string, default_value='png'),
      'image/class/label': tf.FixedLenFeature(
          [], tf.int64, default_value=tf.zeros([], dtype=tf.int64)),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image(),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
  }

  decoder = slim.tfexample_decoder.TFExampleDecoder(
      keys_to_features, items_to_handlers)

  labels_to_names = None
  if dataset_utils.has_labels(dataset_dir):
    labels_to_names = dataset_utils.read_label_file(dataset_dir)

  return slim.dataset.Dataset(
      data_sources=file_pattern,
      reader=reader,
      decoder=decoder,
      num_samples=SPLITS_TO_SIZES[split_name],
      items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
      num_classes=_NUM_CLASSES,
      labels_to_names=labels_to_names)

5、开始训练

接着，修改datasets/dataset_factory.py文件，

将

from datasets import cifar10
from datasets import flowers
from datasets import imagenet
from datasets import mnist

datasets_map = {
    'cifar10': cifar10,
    'flowers': flowers,
    'imagenet': imagenet,
    'mnist': mnist,
}

改成

from datasets import cifar10
from datasets import flowers
from datasets import imagenet
from datasets import mnist
from datasets import eye

datasets_map = {
    'cifar10': cifar10,
    'flowers': flowers,
    'imagenet': imagenet,
    'mnist': mnist,
    'eye': eye,
}

然后，运行以下代码进行训练，

python train_image_classifier.py   --train_dir=saver/inv3_eye_open_and_close   --dataset_name=eye   --dataset_split_name=train   --dataset_dir=images_data/eye_open_and_close   --model_name=inception_v3       --learning_rate_decay_type=fixed   --save_interval_secs=60  --save_summaries_secs=60   --log_every_n_steps=10   --optimizer=rmsprop   --learning_rate=0.0001

运行结果，

OK，跑起来就行了。

6、测试准确率

训练到感觉loss不怎么下降的时候，测试一下它的准确率，命令如下，

python eval_image_classifier.py   --checkpoint_path=saver/inv3_eye_open_and_close/   --eval_dir=saver/inv3_eye_open_and_close/   --dataset_name=eye  --dataset_split_name=validation  --dataset_dir=images_data/eye_open_and_close  --model_name=inception_v3   --batch_size=64

在测试集上的准确率为93.49%，在精度不是要求特别高的情况下还是可以了。

 

如果您感觉本篇博客对您有帮助，请打开支付宝，领个红包支持一下，祝您扫到99元，谢谢～～