智能盘点—钢筋数量AI识别 数钢筋，csv转换成VOC xml格式

csv转txt

import csv
import os,sys
from glob import glob
from PIL import Image

src_img_dir = r'D:\Github\02_kaggle\CCFDF-\train_dataset'
src_txt_dir = r'D:\Github\02_kaggle\CCFDF-\train_label'
src_xml_dir = r'D:\Github\02_kaggle\CCFDF-\train_label_xml'

img_lists = glob(src_img_dir + '/*jpg')
img_basenames = []
for item in img_lists:
    img_basenames.append(os.path.basename(item))

img_names = []
for item in img_basenames:
    temp1, temp2 = os.path.splitext(item)
    img_names.append(temp1)

c = []
filename = r'D:\Github\02_kaggle\CCFDF-\train_labels.csv'
with open(filename) as f:
    reader = csv.reader(f)
    head_now = next(reader)
    l = []
    b = []
    for cow in reader:
        label = cow[0]
        l.append(label)
        bbox = cow[1]
        b.append(bbox)
label = []
for item in l:
    temp1, temp2 = os.path.splitext(item)
    label.append(temp1)

for img in img_names:
    img_file = src_txt_dir + os.sep + img +'.txt'
    fp = open(img_file, 'w')
    for i in range(len(label)):
        if label[i] == img:
            fp.write(str(b[i]))
            fp.write('\n')

txt转xml

import csv
import os,sys
from glob import glob
from PIL import Image

src_img_dir = r'D:\Github\02_kaggle\CCFDF-\train_dataset'
src_txt_dir = r'D:\Github\02_kaggle\CCFDF-\train_label'
src_xml_dir = r'D:\Github\02_kaggle\CCFDF-\train_label_xml'

img_lists = glob(src_img_dir + '/*jpg')
img_basenames = []
for item in img_lists:
    img_basenames.append(os.path.basename(item))

img_names = []
for item in img_basenames:
    temp1, temp2 = os.path.splitext(item)
    img_names.append(temp1)


for img in img_names:
    im = Image.open((src_img_dir + os.sep + img + '.jpg'))
    width, height = im.size
    gt = open(src_txt_dir + os.sep + img + '.txt').read().splitlines()
    xml_file = open((src_xml_dir + os.sep + img + '.xml'), 'w')
    xml_file.write('<annotation>\n')
    xml_file.write('    <folder>VOC2007</folder>\n')
    xml_file.write('    <filename>' + str(img) + '.jpg' + '</filename>\n')
    xml_file.write('    <size>\n')
    xml_file.write('        <width>' + str(width) + '</width>\n')
    xml_file.write('        <height>' + str(height) + '</height>\n')
    xml_file.write('        <depth>3</depth>\n')
    xml_file.write('    </size>\n')

    for img_each_label in gt:
        spt = img_each_label.split(' ')  # 这里如果txt里面是以逗号‘，’隔开的，那么就改为spt = img_each_label.split(',')。
        xml_file.write('    <object>\n')
        xml_file.write('        <name>' + str('good') + '</name>\n')
        xml_file.write('        <pose>Unspecified</pose>\n')
        xml_file.write('        <truncated>0</truncated>\n')
        xml_file.write('        <difficult>0</difficult>\n')
        xml_file.write('        <bndbox>\n')
        xml_file.write('            <xmin>' + str(spt[0]) + '</xmin>\n')
        xml_file.write('            <ymin>' + str(spt[1]) + '</ymin>\n')
        xml_file.write('            <xmax>' + str(spt[2]) + '</xmax>\n')
        xml_file.write('            <ymax>' + str(spt[3]) + '</ymax>\n')
        xml_file.write('        </bndbox>\n')
        xml_file.write('    </object>\n')

    xml_file.write('</annotation>')

 

[参考文献]:https://blog.csdn.net/xunan003/article/details/79052288