File size: 4,173 Bytes
0b8359d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
# Copyright 2017 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 ImageNet ILSVRC 2012 Dataset plus some bounding boxes.

Some images have one or more bounding boxes associated with the label of the
image. See details here: http://image-net.org/download-bboxes

WARNING: Don't use for object detection, in this case all the bounding boxes
of the image belong to just one class.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import tensorflow as tf

slim = tf.contrib.slim

_FILE_PATTERN = '%s-*'

_SPLITS_TO_SIZES = {
    'train': 1281167,
    'validation': 50000,
}

_ITEMS_TO_DESCRIPTIONS = {
    'image': 'A color image of varying height and width.',
    'label': 'The label id of the image, integer between 0 and 999',
    'label_text': 'The text of the label.',
    'object/bbox': 'A list of bounding boxes.',
    'object/label': 'A list of labels, one per each object.',
}

_NUM_CLASSES = 1001


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

  Args:
    split_name: A train/test 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/test 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='jpeg'),
      'image/class/label': tf.FixedLenFeature(
          [], dtype=tf.int64, default_value=-1),
      'image/class/text': tf.FixedLenFeature(
          [], dtype=tf.string, default_value=''),
      'image/object/bbox/xmin': tf.VarLenFeature(
          dtype=tf.float32),
      'image/object/bbox/ymin': tf.VarLenFeature(
          dtype=tf.float32),
      'image/object/bbox/xmax': tf.VarLenFeature(
          dtype=tf.float32),
      'image/object/bbox/ymax': tf.VarLenFeature(
          dtype=tf.float32),
      'image/object/class/label': tf.VarLenFeature(
          dtype=tf.int64),
  }

  items_to_handlers = {
      'image': slim.tfexample_decoder.Image('image/encoded', 'image/format'),
      'label': slim.tfexample_decoder.Tensor('image/class/label'),
      'label_text': slim.tfexample_decoder.Tensor('image/class/text'),
      'object/bbox': slim.tfexample_decoder.BoundingBox(
          ['ymin', 'xmin', 'ymax', 'xmax'], 'image/object/bbox/'),
      'object/label': slim.tfexample_decoder.Tensor('image/object/class/label'),
  }

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

  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)