UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc1 in position 0: invalid start byte.

"""
Usage:
  # # From tensorflow/models/
  # # Create train data:
  python generate_tfrecord.py --csv_input=data/train_labels.csv  --output_path=train.record
  python generate_tfrecord.py --csv_input=data/all_labels.csv  --output_path=train.record


  # # Create test data:
  python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=test.record

  python generate_tfrecord.py --csv_input=data/test_labels.csv  --output_path=data/test.record --image_dir=images/
"""

# # taken from https://github.com/datitran/raccoon_dataset

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.compat.v1.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


# # replace row_label with the name you annotated your images as
def class_text_to_int(row_label):
    if row_label == 'Masked':
        return 1
    elif row_label == 'No_Masked':
        return 2
    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(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()

PS C:\Users\Sumin\TF_Object_Detection2020-master\masks> python generate_tfrecord.py

2020-09-18 09:16:50.716966: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-09-18 09:16:50.760112: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
  File "generate_tfrecord.py", line 109, in <module>
    tf.compat.v1.app.run()
  File "C:\Users\Sumin\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "C:\Users\Sumin\AppData\Roaming\Python\Python38\site-packages\absl\app.py", line 300, in run
    _run_main(main, args)
  File "C:\Users\Sumin\AppData\Roaming\Python\Python38\site-packages\absl\app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "generate_tfrecord.py", line 95, in main
    writer = tf.io.TFRecordWriter(FLAGS.output_path)
  File "C:\Users\Sumin\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\lib\io\tf_record.py", line 298, in __init__
    super(TFRecordWriter, self).__init__(
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc1 in position 40: invalid start byte