深度学习之目标检测从入门到精通——xml转yolo格式

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import glob


classes = ["crazing", "inclusion", "patches", "pitted_surface", "rolled-in_scale", "scratches"]

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_name):
    in_file = open('./ANNOTATIONS/'+image_name[:-3]+'xml')
    out_file = open('./LABELS/'+image_name[:-3]+'txt','w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            print(cls)
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()

if __name__ == '__main__':
    for image_path in glob.glob("./IMAGES/*.jpg"):
        image_name = image_path.split('\\')[-1]
        #print(image_path)
        convert_annotation(image_name)

1. 定义目标类别

classes = ["crazing", "inclusion", "patches", "pitted_surface", "rolled-in_scale", "scratches"]

这一行代码定义了感兴趣的类别列表，即那些我们希望在训练模型时识别的物体类别。

2. 坐标转换函数

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

convert 函数将传入的边界框坐标（xmin, xmax, ymin, ymax）转换为归一化的中心点坐标和宽高。这是因为大多数深度学习模型都使用归一化的坐标系统。

3. 注释转换函数

def convert_annotation(image_name):
    in_file = open('./ANNOTATIONS/'+image_name[:-3]+'xml')
    out_file = open('./LABELS/'+image_name[:-3]+'txt','w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text),
             float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

这个函数处理一个图像的XML标注文件，解析图像中每个对象的坐标，使用convert函数转换坐标，并将结果写入新的文本文件中。

4. 处理所有图像文件

if __name__ == '__main__':
    for image_path in glob.glob("./IMAGES/*.jpg"):
        image_name = image_path.split('\\')[-1]
        convert_annotation(image_name)