Skip to content

Instantly share code, notes, and snippets.

@mnowatzky
Forked from iKhushPatel/create_tfrecord.py
Last active March 12, 2021 14:55
Show Gist options
  • Select an option

  • Save mnowatzky/0fb8b70ceea520a9525accdcdbfea324 to your computer and use it in GitHub Desktop.

Select an option

Save mnowatzky/0fb8b70ceea520a9525accdcdbfea324 to your computer and use it in GitHub Desktop.
"""
Usage:
# From tensorflow/models/
# Create train data:
python create_tfrecord.py --csv_input=data/train_labels.csv --output_path=train.tfrecord
# Create test data:
python create_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.tfrecord
"""
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
import sys
sys.path.append('../')
from object_detection.utils import dataset_util
from object_detection.utils import label_map_util
from collections import namedtuple, OrderedDict
flags = tf.compat.v1.flags
flags.DEFINE_string('csv_input', '', 'data/train_labels.csv')
flags.DEFINE_string('output_path', '', 'data/train.record')
flags.DEFINE_string('image_dir', '', 'images/train')
flags.DEFINE_string('label_map', '', 'data/label_map.pbtxt')
FLAGS = flags.FLAGS
label_dict = label_map_util.get_label_map_dict(FLAGS.label_map)
def class_text_to_int(row_label):
global label_dict
return label_dict.get(row_label, 0)
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.io.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.compat.v1.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.compat.v1.app.run()
@mnowatzky
Copy link
Author

It looks like there is a problem with your label_map.pbtxt file. Are you sure that file is in the correct format?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment