-
Notifications
You must be signed in to change notification settings - Fork 0
/
generate_tfrecord.py
124 lines (101 loc) · 4.18 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
"""
Usage:
# From tensorflow/models/
# Create train data:
python3 generate_tfrecord.py --csv_input=data/train.csv --image_dir==data/images/train --output_path=data/train.record
# Create test data:
python3 generate_tfrecord.py --csv_input=data/test.csv --image_dir==data/images/test --output_path=data/test.record
# Create validation data
python3 generate_tfrecord.py --csv_input=data/validate.csv --image_dir==data/images/validate --output_path=data/validate.record
"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
import os
import io
import pandas as pd
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
# TO-DO replace this with label map
def class_text_to_int(row_label):
if row_label == 'Lionfish':
return 1
elif row_label == 'Diver':
return 2
else:
return 3
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):
# todo check in png vs jpg makes difference
print(os.path.join(path, '{}'.format(group.filename)))
with tf.io.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_image = fid.read()
encoded_image_io = io.BytesIO(encoded_image)
# print(encoded_jpg, encoded_jpg_io)
image = Image.open(encoded_image_io)
width, height = image.size
# print(image.format, width, height)
filename = group.filename.encode('utf8')
# print(filename, filename[len(filename)-4:len(filename)])
# if(filename[len(filename)-4:len(filename)] == '.jpg')):
# todo check in png vs jpg makes difference
image_format = ''
if image.format == 'JPEG':
image_format = b'jpg'
elif image.format == 'PNG':
image_format = b'png'
elif image.format == 'BMP':
image_format = b'bmp'
print(image.format, image_format)
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']))
feature_dict = {
'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_image),
'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)
}
tf_example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
return tf_example
def main(_):
writer = tf.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.compat.v1.app.run()