自用记录 yolov5 训练流程（VOC数据）

一、labelimg标注得到JPEGImages、Annotations文件夹

在同级文件夹下新建labels、images、imageSets文件夹

二、运行dataSet.py

# coding:utf-8

import os
import random
import argparse

parser = argparse.ArgumentParser()
# xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下，注意以下为相对路径
parser.add_argument('--xml_path', default='E:\python_project\yolov5\Dataset\hat\Annotations', type=str, help='input xml label path')
# 数据集的划分，地址选择自己数据下的ImageSets/Main，注意以下为相对路径
parser.add_argument('--txt_path', default='E:\python_project\yolov5\Dataset\hat\imageSets\Main', type=str, help='output txt label path')
opt = parser.parse_args()

trainval_percent = 1.0  # 训练集和验证集所占比例。 这里没有划分测试集
train_percent = 0.9  # 训练集所占比例，可自己进行调整
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)

num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)

file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')

for i in list_index:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        file_trainval.write(name)
        if i in train:
            file_train.write(name)
        else:
            file_val.write(name)
    else:
        file_test.write(name)

file_trainval.close()
file_train.close()
file_val.close()
file_test.close()

生成划分数据txt

三、运行voc_label.py

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

sets = ['train', 'test', 'val']

Imgpath = 'E:\python_project\yolov5\Dataset\hat\images'
xmlfilepath = 'E:\python_project\yolov5\Dataset\hat\Annotations/'
ImageSets_path = 'E:\python_project\yolov5\Dataset\hat\imageSets\Main/'
Label_path = 'E:\python_project\yolov5\Dataset\hat/'
classes = ["hat","person"]



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(xmlfilepath + '%s.xml' % (image_id))
    out_file = open(Label_path + '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')


for image_set in sets:
    if not os.path.exists(Label_path + 'labels/'):
        os.makedirs(Label_path + 'labels/')
    image_ids = open(ImageSets_path + '%s.txt' % (image_set)).read().strip().split()
    list_file = open(Label_path + '%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(Imgpath + '/%s.bmp\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

得到images、labels两个文件夹文件