YOLOv5训练自己的数据集 墨蓝 2023-01-06 05:45 192阅读 0赞 ## 一、准备工作 ## 在data下新建几个文件夹 ![在这里插入图片描述][20210114092311280.png] XML文件放到Annotations 图片文件放到images ## 二、xml转txt(xml格式的label转换为yolo版的label) ## # -*- coding:utf-8 -*- import sys sys.path.append('D:\\Program files\\Anaconda\\libs') import os #os:操作系统相关的信息模块 import random #导入随机函数 #存放原始图片地址 data_base_dir = "./data/images" file_list = [] #建立列表,用于保存图片信息 #读取图片文件,并将图片地址、图片名和标签写到txt文件中 write_file_name = 'ImageXML.txt' write_file = open(write_file_name, "w") #以只写方式打开write_file_name文件 for file in os.listdir(data_base_dir): #file为current_dir当前目录下图片名 if file.endswith(".jpg"): #如果file以jpg结尾 write_name = file #图片路径 + 图片名 + 标签 file_list.append(write_name) #将write_name添加到file_list列表最后 sorted(file_list) #将列表中所有元素随机排列 number_of_lines = len(file_list) #列表中元素个数 #将图片信息写入txt文件中,逐行写入 for current_line in range(number_of_lines): write_file.write(file_list[current_line][:-4] + '\n')#关闭文件 生成ImageXML.txt文件,格式是下面这样的(即图片名称): ![在这里插入图片描述][2021011409271569.png] ## 三、运行voc\_label.py ## # 坐标xml转txt import os import xml.etree.ElementTree as ET classes = ["040500000","040500013","040500021","040500022","040500023","040500031","040500032","040500033"] # 输入名称,必须与xml标注名称一致 def convert(size, box): print(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): print(image_id) in_file = open(r'./data/Annotations/%s.xml' % (image_id), 'rb') # 读取xml文件路径 out_file = open('./data/labels/%s.txt' % (image_id), 'w') # 需要保存的txt格式文件路径 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'): cls = obj.find('code').text if cls not in classes: # 检索xml中的名称 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') image_ids_train = open('./ImageXML.txt').read().strip().split() # 读取xml文件名索引 for image_id in image_ids_train: print(image_id) convert_annotation(image_id) 需要注意,若是有中文路径的话,请这样读文件: open(r'./data/Annotations/%s.xml' % (image_id), 'rb') 接下来就会在data/labels中看到:所有的txt标签 ![在这里插入图片描述][20210114093222414.png] ## 四、切分训练集与测试集 ## 执行train\_test\_split.py import os import random trainval_percent = 0.1 # 可自行进行调节 train_percent = 0.9 xmlfilepath = './data/Annotations' txtsavepath = './data/ImageSets/Main' 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') ftrain = open('./data/ImageSets/Main/train.txt', 'w') ftest = open('./data/ImageSets/Main/test.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() ## 五、生成训练和测试的txt文件(内容为图片的绝对路径) ## 运行path\_trans,data目录下生成train.txt和test.txt import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join sets = ['train', 'test'] classes = ["040500000","040500013","040500021","040500022","040500023","040500031","040500032","040500033"] # 输入名称,必须与xml标注名称一致 # 自己训练的类别 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('data/Annotations/%s.xml' % (image_id), 'rb') out_file = open('data/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('code').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 image_set in sets: if not os.path.exists('data/labels/'): os.makedirs('data/labels/') image_ids = open('data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split() list_file = open('data/%s.txt' % (image_set), 'w') for image_id in image_ids: list_file.write('data/images/%s.jpg\n' % (image_id)) convert_annotation(image_id) list_file.close() ![在这里插入图片描述][20210114093845268.png] ![在这里插入图片描述][20210114095105374.png] ## 六、data目录下新建mydatasets.yaml ## # train and val datasets (image directory or *.txt file with image paths) train: ./data/images # 上面我们生成的train,根据自己的路径进行更改 test: ./data/images # 上面我们生成的test #test: ../coco/test-dev2017.txt # 20k images for submission to https://competitions.codalab.org/competitions/20794 # number of classes nc: 8 #训练的类别 # class names names : ["040500000","040500013","040500021","040500022","040500023","040500031","040500032","040500033"] ## 七、训练 ## 运行train.py python train.py --data data/mydatasets.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --batch-size 16 --epochs 300 [20210114092311280.png]: /images/20221119/8b494b37a50840018afbf4a6dd021a4c.png [2021011409271569.png]: /images/20221119/a32b4a8d4b8642ebb57d496db60525a6.png [20210114093222414.png]: /images/20221119/e442456703194cd0b217f89181b09c33.png [20210114093845268.png]: /images/20221119/9b79b8568c6b492994aaca0775c98ecf.png [20210114095105374.png]: /images/20221119/3823530128cb4da0afe2421611de4369.png
还没有评论,来说两句吧...