images_tag.py
# 該腳本文件需要修改第11-12行，設(shè)置train、val、test的切分的比率
import os
import random
import argparse

parser = argparse.ArgumentParser()
parser.add_argument('--xml_path', default='E:\A\Yolov5\data\dataset\VOCdevkit\Annotations', type=str, help='input xml label path')
parser.add_argument('--txt_path', default='E:\A\Yolov5\data\dataset\VOCdevkit\Imagesets', type=str, help='output txt label path')
opt = parser.parse_args()

trainval_percent = 0.9
train_percent = 0.7 #這里的train_percent 是指占trainval_percent中的
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()
?

voc_to_yolo.py

#該腳本文件需要修改第10行（classes）即可
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
from tqdm import tqdm
import os
from os import getcwd

sets = ['train', 'test','val']
#這里使用要改成自己的類別
classes = ['green', 'off', 'red', 'yellow']


def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
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
x = round(x,6)
w = round(w,6)
y = round(y,6)
h = round(h,6)
return x, y, w, h

#后面只用修改各個文件夾的位置
def convert_annotation(image_id):
#try:
in_file = open('E:\A\Yolov5\data\dataset\VOCdevkit\Annotations/%s.xml' % (image_id), encoding='utf-8')
out_file = open('E:\A\Yolov5\data\dataset\VOCdevkit/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
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))
b1, b2, b3, b4 = b
# 標(biāo)注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " +
" ".join([str(a) for a in bb]) + '\n')
#except Exception as e:
#print(e, image_id)

#這一步生成的txt文件寫在data.yaml文件里
wd = getcwd()
for image_set in sets:
if not os.path.exists('E:\A\Yolov5\data\dataset\VOCdevkit/labels/'):
os.makedirs('E:\A\Yolov5\data\dataset\VOCdevkit/labels/')
image_ids = open('E:\A\Yolov5\data\dataset\VOCdevkit/Imagesets/%s.txt' %
(image_set)).read().strip().split()
list_file = open('E:/A/Yolov5/data/dataset/VOCdevkit/%s.txt' % (image_set), 'w')
for image_id in tqdm(image_ids):
list_file.write('E:/A/Yolov5/data/dataset/VOCdevkit/JPEGImages/%s.png\n' % (image_id))
convert_annotation(image_id)
list_file.close()
data.yaml

# YOLOv5 ?? by Ultralytics, GPL-3.0 license
# COCO 2017 dataset http://cocodataset.org by Microsoft
# Example usage: python train.py --data coco.yaml
# parent
# ├── yolov5
# └── datasets
# └── coco ← downloads here (20.1 GB)


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: E:\A\Yolov5\data\dataset\VOCdevkit # dataset root dir
train: train.txt # train images (relative to 'path') 118287 images
val: val.txt # val images (relative to 'path') 5000 images
test: test.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794

# Classes
nc: 4 # number of classes
names: ['green', 'off', 'red', 'yellow'] # class names