我正在使用 TensorFlow 2.5.0(python 3.9、Ubuntu 20.04 和 Anaconda 3)来创建自定义对象检测器。我已标记我的图像并关注 this教程来达到这一点。但是，在尝试创建我的 tf.record 文件时，我收到以下错误( 请参阅下面列出的最后一行错误 ):
Traceback (most recent call last):
File "/home/database/Custom-Object-Detector-Workspace/Project/scripts/generate_tfrecord.py", line 169, in <module>
tf.app.run()
File "/home/database/python3.9/site-packages/tensorflow/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/home/database/python3.9/site-packages/absl/app.py", line 303, in run
_run_main(main, args)
File "/home/database/python3.9/site-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "/home/database/Custom-Object-Detector-Workspace/Project/scripts/generate_tfrecord.py", line 159, in main
tf_example = create_tf_example(group, path)
File "/home/database/tensorflow/Custom-Object-Detector-Workspace/Project/scripts/generate_tfrecord.py", line 113, in create_tf_example
encoded_jpg = fid.read()
File "/home/database/python3.9/site-packages/tensorflow/python/lib/io/file_io.py", line 117, in read
self._preread_check()
File "/home/database/anaconda3/envs/tensorflow/lib/python3.9/site-packages/tensorflow/python/lib/io/file_io.py", line 79, in _preread_check
self._read_buf = _pywrap_file_io.BufferedInputStream(
tensorflow.python.framework.errors_impl.NotFoundError: /home/database/images/test/DJI_0001_008.jpg; No such file or directory
locate命令会显示我的培训和测试文件夹中的所有文件，其中包含文件名:/images/test/DJI_0001_008_r.jpg
/images/test/DJI_0001_008_r.xml
/images/train/DJI_0001_008_b.jpg
/images/train/DJI_0001_008_b.xml
/images/train/DJI_0001_008_m.jpg
/images/train/DJI_0001_008_m.xml
我该如何解决这个错误？ 这是命名错误吗？如果是这样，最好重命名它们以使“DJI_0001_008”不在任何文件名中？我发现有些图片有 .jpg 扩展名，而另一些有 .JPG 扩展名，这会是一个因素吗？
#######################################################
#Activate Anaconda environment
conda activate tensorflow
#Set workplace directory where the python script is in
cd /home/desired_directory
#run generate_tfrecord.py script, set for creating a tf.record file in the test folder:
python3 generate_tfrecord.py -x /home/tensorflow_ihb/Custom-Object-Detector-Workspace/Project/images/test -l /home/tensorflow_ihb/Custom-Object-Detector-Workspace/Project/annotations/label_map.pbtxt -o /home/tensorflow_ihb/Custom-Object-Detector-Workspace/Project/annotations/test.record -c /home/tensorflow_ihb/Custom-Object-Detector-Workspace/Project/annotations/test.csv
""" Sample TensorFlow XML-to-TFRecord converter
usage: generate_tfrecord.py [-h] [-x XML_DIR] [-l LABELS_PATH] [-o OUTPUT_PATH] [-i IMAGE_DIR] [-c CSV_PATH]
optional arguments:
-h, --help show this help message and exit
-x XML_DIR, --xml_dir XML_DIR
Path to the folder where the input .xml files are stored.
-l LABELS_PATH, --labels_path LABELS_PATH
Path to the labels (.pbtxt) file.
-o OUTPUT_PATH, --output_path OUTPUT_PATH
Path of output TFRecord (.record) file.
-i IMAGE_DIR, --image_dir IMAGE_DIR
Path to the folder where the input image files are stored. Defaults to the same directory as XML_DIR.
-c CSV_PATH, --csv_path CSV_PATH
Path of output .csv file. If none provided, then no file will be written.
"""
import os
import glob
import pandas as pd
import io
import xml.etree.ElementTree as ET
import argparse
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # Suppress TensorFlow logging (1)
import tensorflow.compat.v1 as tf
from PIL import Image
from object_detection.utils import dataset_util, label_map_util
from collections import namedtuple
# Initiate argument parser
parser = argparse.ArgumentParser(
description="Sample TensorFlow XML-to-TFRecord converter")
parser.add_argument("-x",
"--xml_dir",
help="Path to the folder where the input .xml files are stored.",
type=str)
parser.add_argument("-l",
"--labels_path",
help="Path to the labels (.pbtxt) file.", type=str)
parser.add_argument("-o",
"--output_path",
help="Path of output TFRecord (.record) file.", type=str)
parser.add_argument("-i",
"--image_dir",
help="Path to the folder where the input image files are stored. "
"Defaults to the same directory as XML_DIR.",
type=str, default=None)
parser.add_argument("-c",
"--csv_path",
help="Path of output .csv file. If none provided, then no file will be "
"written.",
type=str, default=None)
args = parser.parse_args()
if args.image_dir is None:
args.image_dir = args.xml_dir
label_map = label_map_util.load_labelmap(args.labels_path)
label_map_dict = label_map_util.get_label_map_dict(label_map)
def xml_to_csv(path):
"""Iterates through all .xml files (generated by labelImg) in a given directory and combines
them in a single Pandas dataframe.
Parameters:
----------
path : str
The path containing the .xml files
Returns
-------
Pandas DataFrame
The produced dataframe
"""
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
member[0].text,
int(member[4][0].text),
int(member[4][1].text),
int(member[4][2].text),
int(member[4][3].text)
)
xml_list.append(value)
column_name = ['filename', 'width', 'height',
'class', 'xmin', 'xmax', 'ymin', 'ymax']
xml_df = pd.DataFrame(xml_list, columns=column_name)
xml_df.to_csv("dataset.csv")
return xml_df
def class_text_to_int(row_label):
return label_map_dict[row_label]
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(args.output_path)
path = os.path.join(args.image_dir)
examples = xml_to_csv(args.xml_dir)
grouped = split(examples, 'filename')
for group in grouped:
tf_example = create_tf_example(group, path)
writer.write(tf_example.SerializeToString())
writer.close()
print('Successfully created the TFRecord file: {}'.format(args.output_path))
if args.csv_path is not None:
examples.to_csv(args.csv_path, index=None)
print('Successfully created the CSV file: {}'.format(args.csv_path))
if __name__ == '__main__':
tf.app.run()
最佳答案
我改变了这个，我能够从我的 csv 生成我的 tf.records 测试和训练记录。
请注意，我为测试和训练 CSV 都这样做了
我变了:
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=data/test.record
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=data/test.record --image_dir=images
-桌面
基本上在您的终端代码中，需要将路径添加回您创建 csv 的位置，其中包含所有图像。
关于生成 tf.record 文件时出现 Python 错误 - Tensorflow.python.framework.errors_impl.NotFoundError : No such file or directory，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/68928276/