问题描述
我正在尝试根据this教程使用Tensorflow创建对象检测算法。基本上,当我尝试生成tfrecord并将其放在我的数据文件夹中时,出现错误。详细信息如下。附带说明,我正在使用 Python 3.7.8 。
使用Labelimg软件标记图像后,我在桌面目录中创建了三个文件夹,分别为“数据”,“图像”和“培训”。在图像文件夹中,有两个子文件夹,称为“测试”。和“火车”。以PascalVOC格式标记图像(.xml文件输出)后,我分别将图像移到“测试”和“火车”文件夹中。
我首先使用以下代码将xml文件转换为csv文件,这些代码另存为xml_to_csv.py:
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
def xml_to_csv(path):
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','ymin','xmax','ymax']
xml_df = pd.DataFrame(xml_list,columns=column_name)
return xml_df
def main():
for directory in ['train','test']:
image_path = os.path.join(os.getcwd(),'images/{}'.format(directory))
xml_df = xml_to_csv(image_path)
xml_df.to_csv('data/{}_labels.csv'.format(directory),index=None)
print('Successfully converted xml to csv.')
main()
运行anaconda提示命令python xml_to_csv.py
在我的“数据”文件夹中生成两个CSV文件,并且训练样本的格式正确。
现在,使用以下代码,我需要使用以下代码为火车和测试文件生成tf_record。我只有一类“杂草”,下面进行了编辑。 python文件另存为generate_tfrecord.py。
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 == 'weed':
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.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(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.app.run()
在anaconda命令提示符中,运行命令python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=data/test.record --image_dir=images/
会产生以下错误:
2020-10-15 11:20:43.224624: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-10-15 11:20:43.226712: 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 22,in <module>
flags = tf.app.flags
AttributeError: module 'tensorflow' has no attribute 'app'
如何解决此问题,以便可以创建tfrecord文件直接放在“数据”文件夹中?
解决方法
tensorflow.app
在最新的张量流中不可用
尝试替换
flags = tf.app.flags
和flags = tf.compat.v1.flags
(第14行)
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
和writer = tf.io.TFRecordWriter(FLAGS.output_path)
(第77行)
tf.app.run()
和tf.compat.v1.app.run()
(最后一行)