python 3.8.x and tensorflow 2.x changes fix

generate_tfrecord_for_py3.8.x.py

@@ -0,0 +1,104 @@
+"""
+Usage:
+  # From tensorflow/models/
+  # Create train data:
+  python generate_tfrecord.py --csv_input=images/train_labels.csv --image_dir=images/train --output_path=train.record
+
+  # Create test data:
+  python generate_tfrecord.py --csv_input=images/test_labels.csv  --image_dir=images/test --output_path=test.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
+
+import argparse
+
+from PIL import Image
+from object_detection.utils import dataset_util
+from collections import namedtuple, OrderedDict
+
+# construct the argument parse and parse the arguments
+ap = argparse.ArgumentParser()
+ap.add_argument("-c", "--csv_input", required=True,help="csv dosyasının yeri (csv file)")
+ap.add_argument("-i", "--image_dir", required=True,help="gorsellerin olduğu yer (get img files from)")
+ap.add_argument("-o", "--output_path", required=True,help="nereye kaydedelim (save img files to)")
+args = vars(ap.parse_args())
+
+
+# TO-DO replace this with label map
+def class_text_to_int(row_label):
+    if row_label == 'maske':
+        return 1
+    else:
+        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.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.io.TFRecordWriter(args["output_path"])
+    path = os.path.join(os.getcwd(), args["image_dir"])
+    examples = pd.read_csv(args["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(), args["output_path"])
+    print('Successfully created the TFRecords: {}'.format(output_path))
+
+
+if __name__ == '__main__':
+    main()
+    #tf.app.run()