-
Notifications
You must be signed in to change notification settings - Fork 35
/
convert.py
239 lines (181 loc) · 7.61 KB
/
convert.py
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
# 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.
# ==============================================================================
r"""Convert Arts data to TFRecords of TF-Example protos.
This module reads the image files that make up the Arts data and creates
two TFRecord datasets: one for train and one for validation.
Each TFRecord dataset is comprised of a set of TF-Example
protocol buffers, each of which contain a single image and label.
The script should take about a minute to run.
"""
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
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string(
'dataset_dir',
None,
'The directory where the output TFRecords are saved.')
tf.app.flags.DEFINE_boolean(
'check_image',
False,
'Validate the image files only, no processing.')
# Percentage of images to set aside for the validation set.
_PERCENT_VALIDATION = .25
# Seed for repeatability.
_RANDOM_SEED = 0
# The number of shards per dataset split.
_NUM_SHARDS = 5
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.
"""
art_root = os.path.join(dataset_dir, 'met_art')
directories = []
class_names = []
for filename in os.listdir(art_root):
path = os.path.join(art_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):
output_filename = 'arts_%s_%05d-of-%05d.tfrecord' % (
split_name, shard_id, _NUM_SHARDS)
return os.path.join(dataset_dir, output_filename)
def _check_image(filenames):
"""Converts the given filenames to a TFRecord dataset.
filenames: A list of absolute paths to png or jpg images.
"""
with tf.Graph().as_default():
image_reader = ImageReader()
with tf.Session('') as sess:
for i in range(len(filenames)):
sys.stdout.write('\r>> Checking image %d/%d' % (
i+1, len(filenames) ))
sys.stdout.flush()
try:
# Read the filename:
image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()
height, width = image_reader.read_image_dims(sess, image_data)
except:
sys.stdout.write('\n Error in image: %s\n' % (filenames[i]))
sys.stdout.write('\n')
sys.stdout.flush()
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.write('>> Converting image %s \n' % (filenames[i]))
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 _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 main(_):
"""Runs the conversion operation.
Args:
dataset_dir: The dataset directory where the dataset is stored.
"""
if not FLAGS.dataset_dir:
raise ValueError('Please specify the dataset directory with --dataset_dir')
if _dataset_exists(FLAGS.dataset_dir):
print('Dataset files already exist. Exiting without re-creating them.')
return
photo_filenames, class_names = _get_filenames_and_classes(FLAGS.dataset_dir)
class_names_to_ids = dict(zip(class_names, range(len(class_names))))
if FLAGS.check_image:
_check_image(photo_filenames)
return
# Divide into train and test:
random.seed(_RANDOM_SEED)
random.shuffle(photo_filenames)
_NUM_VALIDATION = int(len(photo_filenames) * _PERCENT_VALIDATION)
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,
FLAGS.dataset_dir)
_convert_dataset('validation', validation_filenames, class_names_to_ids,
FLAGS.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, FLAGS.dataset_dir)
print('\nFinished converting the Arts dataset!')
if __name__ == '__main__':
tf.app.run()