voc数据集_yolov3训练数据集处理(voc_label.py)讲解,小白入门

yolov3训练数据label值为"类别, 中心点x坐标比, 中心点y坐标比, 宽度比, 高度比", 后四个比值均为相对于原图的数据比, 取值范围是0到1. 具体操作可查看voc_label.py文件:

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

sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]

# 选取VOC其中的20类(VOC数据集一共20类),作为训练数据,此处可以任意修改为自己需要的数据类目名称. 如果数据集中添加的有自己的数据集,需要根据情况添加
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]


def convert(size, box): # size:(原图w,原图h) , box:(xmin,xmax,ymin,ymax) 
    dw = 1./size[0]     # 1/w
    dh = 1./size[1]     # 1/h
    x = (box[0] + box[1])/2.0   # 物体在图中的中心点x坐标
    y = (box[2] + box[3])/2.0   # 物体在图中的中心点y坐标
    w = box[1] - box[0]         # 物体实际像素宽度
    h = box[3] - box[2]         # 物体实际像素高度
    x = x*dw    # 物体中心点x的坐标比(相当于 x/原图w)
    w = w*dw    # 物体宽度的宽度比(相当于 w/原图w)
    y = y*dh    # 物体中心点y的坐标比(相当于 y/原图h)
    h = h*dh    # 物体宽度的宽度比(相当于 h/原图h)
    return (x,y,w,h)    # 返回 相对于原图的物体中心点的x坐标比,y坐标比,宽度比,高度比,取值范围[0-1]

def convert_annotation(year, image_id):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')  # 生成每个jpg图片对应的label文件,内容为: "物体类别,中心点x坐标比,中心点y坐标比,宽度比,高度比",比值均是相对于原图,每行一个物体数据
    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'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            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()

for year, image_set in sets:
    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')    # 生成各个训练集的jpg文件列表
    for image_id in image_ids:
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpgn'%(wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()