Yolov5训练自己的数据集（超详细）

2022-09-28 05:06| 来源: 网络整理| 查看: 265

一、从官网下载最新的yolov5代码二、新建VOCData文件夹 Yolov5训练自己的数据集（超详细）三、VOCData文件夹结构 1、新建Annotations文件夹，存放标签简单的xml文件，应该长这样复杂的xml文件，应该长这个样子 2、新建images文件夹，存放图片数据注意：需要观察自己的图片文件的后缀名，后面需要用到，不然可能出现程序找不到图片的情况 3、新建split_train_val.py，用来划分训练集与验证集

# 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 parser.add_argument('--xml_path', default='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 parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path') opt = parser.parse_args() trainval_percent = 0.7 # 训练集和验证集所占比例。这里没有划分测试集 train_percent = 0.5 # 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()

运行之后，会发现VOCData文件夹里面多了ImageSets文件夹 Yolov5训练自己的数据集（超详细）里面包括四个txt文件 txt文件存储了图片的序号 4、新建xml_to_yolo.py，用于将xml格式的标签转化为yolo格式的标签对于简单的xml文件，用下列代码

# -*- coding: utf-8 -*- import xml.etree.ElementTree as ET import os from os import getcwd sets = ['train', 'val', 'test'] classes = ["ship"] # 改成自己的类别 abs_path = os.getcwd() print(abs_path) 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 return x, y, w, h def convert_annotation(image_id): in_file = open('D:/Project/yolov5Project/yolov5/VOCData/Annotations/%s.xml' % (image_id), encoding='UTF-8') out_file = open('D:/Project/yolov5Project/yolov5/VOCData/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 # 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 # 标注越界修正 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') wd = getcwd() for image_set in sets: if not os.path.exists('D:/Project/yolov5Project/yolov5/VOCData/labels/'): os.makedirs('D:/Project/yolov5Project/yolov5/VOCData/labels/') image_ids = open('D:/Project/yolov5Project/yolov5/VOCData/ImageSets/Main/%s.txt' % (image_set)).read().strip().split() if not os.path.exists('D:/Project/yolov5Project/yolov5/VOCData/dataSet_path/'): os.makedirs('D:/Project/yolov5Project/yolov5/VOCData/dataSet_path/') list_file = open('dataSet_path/%s.txt' % (image_set), 'w') # 这行路径不需更改，这是相对路径 for image_id in image_ids: list_file.write('D:/Project/yolov5Project/yolov5/VOCData/images/%s.jpg\n' % (image_id)) convert_annotation(image_id) list_file.close()

对于复杂的xml文件，用下列代码。该程序的功能：将Class_ID属于aircraft_carrier列表的物体标记为类别0，将Class_ID属于warcraft列表的物体标记为类别1，将Class_ID属于aircraft_carrier列表的物体标记为类别2，将Class_ID属于merchant_ship列表的物体标记为类别3。然后转化为yolo格式标签。

# -*- coding: utf-8 -*- import xml.etree.ElementTree as ET import os from os import getcwd Class_1_num = 0 Class_2_num = 0 Class_3_num = 0 Class_4_num = 0 sets = ['train','test','val'] classes = ["ship"] # 改成自己的类别 abs_path = os.getcwd() print(abs_path) aircraft_carrier = [100000005,100000006,100000012,100000013,100000031,100000032,100000033] warcraft = [100000007,100000008,100000009,100000010,100000011,100000014,100000015,100000016,100000017,100000019,100000003,100000029] merchant_ship = [100000018,100000022,100000024,100000018,100000025,100000026,100000030] Submarine = [100000027] 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 return x, y, w, h def convert_annotation(image_id): global Class_1_num,Class_2_num,Class_3_num,Class_4_num 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() HRSC_Objects = root.find('HRSC_Objects') HRSC_Object = HRSC_Objects.find('HRSC_Object') if HRSC_Object!=None: for HRSC_Object in HRSC_Objects.iter('HRSC_Object'): Class_ID = int(HRSC_Object.find('Class_ID').text) if Class_ID in aircraft_carrier or Class_ID in warcraft or Class_ID in merchant_ship or Class_ID in Submarine: w = int(root.find('Img_SizeWidth').text) h = int(root.find('Img_SizeHeight').text) b = (float(HRSC_Object.find('box_xmin').text),float(HRSC_Object.find('box_xmax').text),float(HRSC_Object.find('box_ymin').text),float(HRSC_Object.find('box_ymax').text)) b1, b2, b3, b4 = b # 标注越界修正 if b2 > w: b2 = w if b4 > h: b4 = h b = (b1, b2, b3, b4) bb = convert((w, h), b) if Class_ID in aircraft_carrier: Class_1_num = Class_1_num+1 Class = 0 if Class_ID in warcraft: Class_2_num = Class_2_num+1 Class = 1 if Class_ID in merchant_ship: Class_3_num = Class_3_num+1 Class = 2 if Class_ID in Submarine: Class_4_num = Class_4_num+1 Class = 3 out_file.write(str(Class) + " " + " ".join([str(a) for a in bb]) + '\n') else: print('do not caculate'+str(Class_ID)) continue wd = getcwd() 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() if not os.path.exists('./dataSet_path/'): os.makedirs('./dataSet_path/') list_file = open('./dataSet_path/%s.txt' % (image_set), 'w') # 这行路径不需更改，这是相对路径 for image_id in image_ids: print('目前的图片id为：'+image_id) list_file.write('D:/Project/yolov5Project/yolov5_three_classifications/VOCData/images/%s.bmp\n' % (image_id)) convert_annotation(image_id) list_file.close() print(Class_1_num) print(Class_2_num) print(Class_3_num) print(Class_4_num)

运行后，会发现多了两个文件 Yolov5训练自己的数据集（超详细） dataSet_path文件中存储了训练集、测试集、验证集的绝对路径 labels存储了yolo格式的标签 5、进入data文件夹，新建mycov.yaml myvoc.yaml的内容，其中，train与val为训练集与验证集列表的绝对路径 6、修改权重文件yolov5s.yaml Yolov5训练自己的数据集（超详细）把类别改为我们设置的类别数量 7、开始训练（1）训练