-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgenerate_tfrecord.py
157 lines (138 loc) · 4.64 KB
/
generate_tfrecord.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
#based on https://github.com/datitran/raccoon_dataset/blob/master/generate_tfrecord.py
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
from tensorflow.python.framework.versions import VERSION
if VERSION >= "2.0.0a0":
import tensorflow.compat.v1 as tf
else:
import tensorflow as tf
from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict
flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
flags.DEFINE_string('image_dir', '', 'Path to images')
FLAGS = flags.FLAGS
def class_text_to_int(row_label):
if row_label == 'id_1':
return 1
elif row_label == 'id_2':
return 2
elif row_label == 'id_3':
return 3
elif row_label == 'id_4':
return 4
elif row_label == 'id_5':
return 5
elif row_label == 'id_6':
return 6
elif row_label == 'id_7':
return 7
elif row_label == 'id_8':
return 8
elif row_label == 'id_9':
return 9
elif row_label == 'id_10':
return 10
elif row_label == 'id_11':
return 11
elif row_label == 'id_12':
return 12
elif row_label == 'id_13':
return 13
elif row_label == 'id_14':
return 14
elif row_label == 'id_15':
return 15
elif row_label == 'id_16':
return 16
elif row_label == 'id_17':
return 17
elif row_label == 'id_18':
return 18
elif row_label == 'id_19':
return 19
elif row_label == 'id_20':
return 20
elif row_label == 'id_21':
return 21
elif row_label == 'id_22':
return 22
elif row_label == 'id_23':
return 23
elif row_label == 'id_24':
return 24
elif row_label == 'id_25':
return 25
elif row_label == 'id_26':
return 26
elif row_label == 'id_27':
return 27
elif row_label == 'id_28':
return 28
elif row_label == 'id_29':
return 29
elif row_label == 'id_30':
return 30
elif row_label == 'bulls_eye':
return 31
else:
return None
def split(df, group):
data = namedtuple('data', ['filename', 'object'])
gb = df.groupby(group)
return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
def create_tf_example(group, path):
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_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(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def main(_):
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
path = os.path.join(FLAGS.image_dir)
examples = pd.read_csv(FLAGS.csv_input)
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
output_path = os.path.join(os.getcwd(), FLAGS.output_path)
print('Successfully created the TFRecords: {}'.format(output_path))
if __name__ == '__main__':
tf.app.run()