PyTorch-YOLO V5训练自己的VOC数据集（四）

VOC数据集目录结构

           ----voc
                       ----Annotations
                       ----ImageSets
                                    ----Main
                       ----JPEGImages

在根目录下新建makeTXT.py，将数据集划分，并且在Main文件夹下构建4个TXT：train.txt，test.txt，trainval.txt，val.txt。代码如下：

import os
import random
 
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = './Annotations'
txtsavepath = './ImageSets'
total_xml = os.listdir(xmlfilepath)
 
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
 
ftrainval = open('./ImageSets/Main/trainval.txt', 'w')
ftest = open('./ImageSets/Main/test.txt', 'w')
ftrain = open('./ImageSets/Main/train.txt', 'w')
fval = open('./ImageSets/Main/val.txt', 'w')
 
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)
 
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

运行makeTXT.py，ImageSets\Main文件夹生成如下文件：

在根目录下新建voc_label.py，生成labels文件夹，及用于yolov5训练的train.txt，text.txt，val.txt。代码如下：

#encoding='utf-8'
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test','val']
classes = ["FP"]
 
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_id):
    in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('labels/%s.txt' % (image_id), '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'):
        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()
print(wd)
for image_set in sets:
    if not os.path.exists('labels/'):
        os.makedirs('labels/')
    image_ids = open('ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('images/%s.bmp\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

运行voc_label.py，用于训练的数据集标注文件如下图：

借助COCO数据集格式，将上述文件放在COCO128数据集中：

将JPEGImages文件中的所有图像放在datasets\coco128\images\train2017文件下，将voc_label.py生成的labels文件中所有标注文件放在datasets\coco128\labels\train2017文件下。

将voc格式的数据集转换成yolo格式的数据集进行训练和预测。