Yolo数据集格式
yolo格式详解:
1代表类别,后面小数依次是目标框x中心点坐标归一化处理,y中心点坐标归一化处理,目标框宽和高进行归一化处理(这里的归一化是按照图片的宽高进行计算的)
转换代码
方法一
import os
import glob
from PIL import Image
voc_annotations = 'D:/yolo_test_review/annotations/'
yolo_txt = 'D:/yolo_test_review/yolov3/labels/'
img_path = 'D:/yolo_test_review/yolov3/images/'
labels = ['A', 'B', 'C'] # label for datasets
# 图像存储位置
src_img_dir = img_path # 添加你的路径
# 图像的txt文件存放位置
src_txt_dir = yolo_txt
src_xml_dir = voc_annotations
img_Lists = glob.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 + '/' + img + '.jpg'))
width, height = im.size
# 打开txt文件
gt = open(src_txt_dir + '/' + img + '.txt').read().splitlines()
print(gt)
if gt:
# 将主干部分写入xml文件中
xml_file = open((src_xml_dir + '/' + 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')
# write the region of image on xml file
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(',')。
print(f'spt:{spt}')
xml_file.write(' <object>\n')
xml_file.write(' <name>' + str(labels[int(spt[0])]) + '</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')
center_x = round(float(spt[1].strip()) * width)
center_y = round(float(spt[2].strip()) * height)
bbox_width = round(float(spt[3].strip()) * width)
bbox_height = round(float(spt[4].strip()) * height)
xmin = str(int(center_x - bbox_width / 2))
ymin = str(int(center_y - bbox_height / 2))
xmax = str(int(center_x + bbox_width / 2))
ymax = str(int(center_y + bbox_height / 2))
xml_file.write(' <xmin>' + xmin + '</xmin>\n')
xml_file.write(' <ymin>' + ymin + '</ymin>\n')
xml_file.write(' <xmax>' + xmax + '</xmax>\n')
xml_file.write(' <ymax>' + ymax + '</ymax>\n')
xml_file.write(' </bndbox>\n')
xml_file.write(' </object>\n')
xml_file.write('</annotation>')
方法二
import os
from PIL import Image
import glob
yolo_img = 'D:/shuichi_test/yolo/img/'
yolo_txt = 'D:/shuichi_test/yolo/txt/'
voc_xml = 'D:/shuichi_test/voc/annotations/'
# 目标类别
labels = ['HLB', 'health', 'ill']
# 匹配文件路径下的所有jpg文件,并返回列表
img_glob = glob.glob(yolo_img + '*.jpg')
img_base_names = []
for img in img_glob:
# os.path.basename:取文件的后缀名
img_base_names.append(os.path.basename(img))
img_pre_name = []
for img in img_base_names:
# os.path.splitext:将文件按照后缀切分为两块
temp1, temp2 = os.path.splitext(img)
img_pre_name.append(temp1)
print(f'imgpre:{img_pre_name}')
for img in img_pre_name:
with open(voc_xml + img + '.xml', 'w') as xml_files:
image = Image.open(yolo_img + img + '.jpg')
img_w, img_h = image.size
xml_files.write('<annotation>\n')
xml_files.write(' <folder>folder</folder>\n')
xml_files.write(f' <filename>{img}.jpg</filename>\n')
xml_files.write(' <source>\n')
xml_files.write(' <database>Unknown</database>\n')
xml_files.write(' </source>\n')
xml_files.write(' <size>\n')
xml_files.write(f' <width>{img_w}</width>\n')
xml_files.write(f' <height>{img_h}</height>\n')
xml_files.write(f' <depth>3</depth>\n')
xml_files.write(' </size>\n')
xml_files.write(' <segmented>0</segmented>\n')
with open(yolo_txt + img + '.txt', 'r') as f:
# 以列表形式返回每一行
lines = f.read().splitlines()
for each_line in lines:
line = each_line.split(' ')
xml_files.write(' <object>\n')
xml_files.write(f' <name>{labels[int(line[0])]}</name>\n')
xml_files.write(' <pose>Unspecified</pose>\n')
xml_files.write(' <truncated>0</truncated>\n')
xml_files.write(' <difficult>0</difficult>\n')
xml_files.write(' <bndbox>\n')
center_x = round(float(line[1]) * img_w)
center_y = round(float(line[2]) * img_h)
bbox_w = round(float(line[3]) * img_w)
bbox_h = round(float(line[4]) * img_h)
xmin = str(int(center_x - bbox_w / 2))
ymin = str(int(center_y - bbox_h / 2))
xmax = str(int(center_x + bbox_w / 2))
ymax = str(int(center_y + bbox_h / 2))
xml_files.write(f' <xmin>{xmin}</xmin>\n')
xml_files.write(f' <ymin>{ymin}</ymin>\n')
xml_files.write(f' <xmax>{xmax}</xmax>\n')
xml_files.write(f' <ymax>{ymax}</ymax>\n')
xml_files.write(' </bndbox>\n')
xml_files.write(' </object>\n')
xml_files.write('</annotation>')
生成的XML文件
版权声明:本文为CSDN博主「阿吉的CV之路」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/qq_35140742/article/details/118157598
暂无评论