Python实现常见数据格式转换的方法详解
目录
- xml_to_csv
- csv_to_tfrecord
xml_to_csv
代码如下:
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(): print(os.getcwd()) # 结果为E:\python_code\crack\models_trainning # ToDo 根据自己实际目录修改 # image_path = os.path.join(os.getcwd(), 'dataset/crack/test') # 根据自己实际目录修改,或者使用下面的路径 image_path = 'E:/python_code/crack/models_trainning/dataset/crack/test' print(image_path) xml_df = xml_to_csv(image_path) xml_df.to_csv('./dataset/crack/train/crack_test.csv', index=None) # 根据自己实际目录修改 print('Successfully converted xml to csv.') main()
这里需要注意的是,这里的话我们只需要修改路径,就不需要在终端运行(每次需要先去该目录下)了,对于不玩linux的同学比较友好。
print(os.getcwd())
结果为E:\python_code\crack\models_trainning
image_path = os.path.join(os.getcwd(), 'dataset/crack/test') image_path = 'E:/python_code/crack/models_trainning/dataset/crack/test'
以上两种图片路径方法都可以,一个采用的是os.path.join()进行路径拼接。
xml_df.to_csv('./dataset/crack/train/crack_test.csv', index=None)
保存为csv的路径可以随意写
结果如下
csv_to_tfrecord
# -*- coding: utf-8-*- 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 tensorflow.compat.v1 as tf from PIL import Image from research.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 = flags.FLAGS # 将分类名称转成ID号 def class_text_to_int(row_label): if row_label == 'crack': return 1 # elif row_label == 'car': # return 2 # elif row_label == 'person': # return 3 # elif row_label == 'kite': # return 4 else: print('NONE: ' + row_label) # 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): print(os.path.join(path, '{}'.format(group.filename))) 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 + '.jpg').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(csv_input, output_path, imgPath): writer = tf.python_io.TFRecordWriter(output_path) path = imgPath examples = pd.read_csv(csv_input) 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 TFRecords: {}'.format(output_path)) if __name__ == '__main__': # ToDo 修改相应目录 imgPath = r'E:\python_code\crack\models_trainning\dataset\crack\test' output_path = 'dataset/crack/test/crack_test.record' csv_input = 'dataset/crack/test/crack_test.csv' main(csv_input, output_path, imgPath)
如xml_to_csv类似,只要把路径改好即可
imgPath是图片所在文件夹路径
output_path是tfrecord生成的路径
csv_iinput是使用的csv的路径
当然,你可能会出现下面报错,起初笔者还以为是编码问题,可是始终未能解决。后来仔细检查发现,是自己路径搞错了,因此大家出现这个错误的时候,检查一下路径先。
到此这篇关于Python实现常见数据格式转换的方法详解的文章就介绍到这了,更多相关Python数据格式转换内容请搜索我们以前的文章或继续浏览下面的相关文章希望大家以后多多支持我们!
赞 (0)