/
create_pascal_tf_record.py
184 lines (158 loc) · 7.28 KB
/
create_pascal_tf_record.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
# 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.
# ==============================================================================
r"""Convert raw PASCAL dataset to TFRecord for object_detection.
Example usage:
python object_detection/dataset_tools/create_pascal_tf_record.py \
--data_dir=/home/user/VOCdevkit \
--year=VOC2012 \
--output_path=/home/user/pascal.record
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import hashlib
import io
import logging
import os
import sys
sys.path.append(r'G:\MutilDetect\models\research')
sys.path.append(r'G:\MutilDetect\models\research\slim')
from lxml import etree
import PIL.Image
import tensorflow as tf
from object_detection.utils import dataset_util
from glob import glob
# flags = tf.app.flags
# flags.DEFINE_string('data_dir', r'G:\DroneDetect\DroneDetect\Customize\src_dir',
# 'Root directory to raw PASCAL VOC dataset.')
# flags.DEFINE_string('set', 'val', 'Convert training set, validation set or '
# 'merged set.')
# flags.DEFINE_string('annotations_dir', 'Annotations',
# '(Relative) path to annotations directory.')
# flags.DEFINE_string('output_path', './pascal.record', 'Path to output TFRecord')
# flags.DEFINE_boolean('ignore_difficult_instances', False, 'Whether to ignore '
# 'difficult instances')
# FLAGS = flags.FLAGS
def dict_to_tf_example(data,
dataset_directory,
label_map_dict,
ignore_difficult_instances=False):
"""Convert XML derived dict to tf.Example proto.
Notice that this function normalizes the bounding box coordinates provided
by the raw data.
Args:
data: dict holding PASCAL XML fields for a single image (obtained by
running dataset_util.recursive_parse_xml_to_dict)
dataset_directory: Path to root directory holding PASCAL dataset
label_map_dict: A map from string label names to integers ids.
ignore_difficult_instances: Whether to skip difficult instances in the
dataset (default: False).
image_subdirectory: String specifying subdirectory within the
PASCAL dataset directory holding the actual image data.
Returns:
example: The converted tf.Example.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
img_path =data['filename']
full_path = os.path.join(dataset_directory, img_path)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
key = hashlib.sha256(encoded_jpg).hexdigest()
width = int(data['size']['width'])
height = int(data['size']['height'])
xmin = []
ymin = []
xmax = []
ymax = []
classes = []
classes_text = []
truncated = []
poses = []
difficult_obj = []
if 'object' in data:
for obj in data['object']:
difficult = bool(int(obj['difficult']))
if ignore_difficult_instances and difficult:
continue
difficult_obj.append(int(difficult))
xmin.append(float(obj['bndbox']['xmin']) / width)
ymin.append(float(obj['bndbox']['ymin']) / height)
xmax.append(float(obj['bndbox']['xmax']) / width)
ymax.append(float(obj['bndbox']['ymax']) / height)
classes_text.append(obj['name'].encode('utf8'))
classes.append(label_map_dict[obj['name']])
truncated.append(int(obj['truncated']))
poses.append(obj['pose'].encode('utf8'))
example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(
data['filename'].encode('utf8')),
'image/source_id': dataset_util.bytes_feature(
data['filename'].encode('utf8')),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
'image/object/difficult': dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated': dataset_util.int64_list_feature(truncated),
'image/object/view': dataset_util.bytes_list_feature(poses),
}))
return example
def generate_tfrecord(data_dir,tf_recod_path):
data_dir = os.path.abspath(data_dir)
output_path = os.path.abspath(tf_recod_path)
ignore_difficult_instances = False
writer = tf.python_io.TFRecordWriter(output_path)
label_map_dict = {'0':0,'1': 1}
from glob import glob
xml_files=glob(os.path.join(data_dir,'*.xml'))
img_files=glob(os.path.join(data_dir,'*.jpg'))+ \
glob(os.path.join(data_dir, '*.png'))
get_bld_filename=lambda path:os.path.splitext(os.path.basename(path))[0]
get_bld_set=lambda filenames:set(map(get_bld_filename,filenames))
xml_4_check=get_bld_set(xml_files)
img_4_check=get_bld_set(img_files)
diff=xml_4_check.symmetric_difference(img_4_check)
if len(diff)!=0:
for item in diff:
print(item,'xml or img file lost')
raise('please check the data over and over again')
for idx, (xml_path,img_path) in enumerate(zip(xml_files,img_files)):
if idx % 100 == 0:
print('On image {} of {}'.format(idx, len(xml_files)))
with tf.gfile.GFile(xml_path, 'r') as fid:
xml_str = fid.read().encode('utf8')
xml = etree.fromstring(xml_str)
data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
data['folder'] = data_dir
data['filename']=img_path
tf_example = dict_to_tf_example(data, data_dir, label_map_dict,
ignore_difficult_instances)
writer.write(tf_example.SerializeToString())
writer.close()
if __name__ == '__main__':
generate_tfrecord(r'I:\final_dataset_2019_0611\phatom=0_mavic=1_300x300',
r'I:\final_dataset_2019_0611\train.record')