Yolov3 darknet ：voc_label.py 詳解

在darknet版本的yolov3中，我們要將每張圖片對應的XML文件轉換爲一個txt文件，包含邊框的信息：

import xml.etree.ElementTree as ET
import os

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

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):
    dw = 1./(size[0])
    dh = 1./(size[1])
    # 爲什麼要減去1 ？ 不明白
    x = (box[0] + box[1])/2.0 -1
    y = (box[2] + box[3])/2.0 -1
    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(year, image_id):
    in_file = open('D:/Datasets/VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id))
    out_file = open("D:/Datasets/VOCdevkit/VOC%s/labels/%s.txt" % (year, image_id), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    # find size
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

	# find object
    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)
        # find bndbox of each object
        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')

for year, image_set in sets:
    if not os.path.exists('D:/Datasets/VOCdevkit/VOC%s/labels/' % (year)):
        os.makedirs('D:/Datasets/VOCdevkit/VOC%s/labels/' % (year))
    image_ids = open('D:/Datasets/VOCdevkit/VOC%s/ImageSets/Main/%s.txt' % (year, image_set)).read().strip().split()
    list_file = open('D:/Datasets/VOCdevkit/VOC%s/%s_%s.txt' % (year, year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('D:/Datasets/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n' % (year, image_id))
        convert_annotation(year, image_id)
    list_file.close()

# os.system("cmd")          執行過程中會輸出顯示cmd命令執行的信息
# 將幾個文件合併爲一個文件： $cat file1 file2 > file
os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt")
os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")