1、制作voc2007数据集

2007标准格式为：

（1）2007具体结构内容如下：

C:\Users\lindsay\Desktop\yolov5\data\VOC2007\images存放我的jpg图片

C:\Users\lindsay\Desktop\yolov5\data\VOC2007\Annotations存放对应的xml文件 C:\Users\lindsay\Desktop\yolov5\data\VOC2007\ImageSets\Main存放划分的训练集、验证集等图片名称的txt文档

（2）运行voc2yolo4.py划分数据集

import os import random xmlfilepath=r'Annotations' saveBasePath=r"ImageSets/Main/" trainval_percent=0.66 train_percent=0.5 temp_xml = os.listdir(xmlfilepath) total_xml = [] for xml in temp_xml: if xml.endswith(".xml"): total_xml.append(xml) 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) print("train and val size",tv) print("traub suze",tr) ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w') ftest = open(os.path.join(saveBasePath,'test.txt'), 'w') ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w') fval = open(os.path.join(saveBasePath,'val.txt'), 'w') for i in list: name=total_xml[i][:-4]+'\n' if i in trainval: ftrainval.write(name) if i in train: ftrain.write(name) else: fval.write(name) else: ftest.write(name) ftrainval.close() ftrain.close() fval.close() ftest .close()

运行完毕后在C:\Users\lindsay\Desktop\yolov5\data\VOC2007\ImageSets\Main生成了划分的训练集、验证集等图片名称的txt文档

（3）运行voc_label.py生成对应图片的label的坐标：

# -*- coding: utf-8 -*- import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join sets = ['train', 'val', 'test'] classes = ['face'] abs_path = os.getcwd() 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('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/Annotations/%s.xml' % (image_id)) out_file = open('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/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() for image_set in sets: if not os.path.exists('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/labels/'): os.makedirs('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/labels/') image_ids = open('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/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('C:/Users/lindsay/Desktop/yolov5/data/VOC2007/images/%s.jpg\n' % (image_id)) convert_annotation(image_id) list_file.close() # os.system("cat 2007_train.txt 2007_val.txt > train.txt")

运行完毕后在C:\Users\lindsay\Desktop\yolov5\data\VOC2007\labels里面生成了如下文件： 在C:\Users\lindsay\Desktop\yolov5\data生成test、train、val三个文件，文件里包含了图片的路径以及名称

（4）完成以上步骤后整体数据集结构如下：

VOC2007 -Annotations -xxx.xml -images -xxx.jpg -ImageSets -Main -train.txt -trainval.txt -test.txt -val.txt -labels -xxx.txt

2、创建两个yaml文件

创建./data/voc2007.yaml

train: C:/Users/lindsay/Desktop/yolov5/data/train.txt val: C:/Users/lindsay/Desktop/yolov5/data/val.txt # number of classes nc: 1 # class names names: ['face']

创建./models/yolov5s.yaml

# parameters nc: 1 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # layer channel multiple # anchors anchors: - [10,13, 16,30, 33,23] # P3/8 - [30,61, 62,45, 59,119] # P4/16 - [116,90, 156,198, 373,326] # P5/32 # YOLOv5 backbone backbone: # [from, number, module, args] [[-1, 1, Focus, [64, 3]], # 0-P1/2 [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 [-1, 3, BottleneckCSP, [128]], [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 [-1, 9, BottleneckCSP, [256]], [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 [-1, 9, BottleneckCSP, [512]], [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 [-1, 1, SPP, [1024, [5, 9, 13]]], [-1, 3, BottleneckCSP, [1024, False]], # 9 ] # YOLOv5 head head: [[-1, 1, Conv, [512, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 6], 1, Concat, [1]], # cat backbone P4 [-1, 3, BottleneckCSP, [512, False]], # 13 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 4], 1, Concat, [1]], # cat backbone P3 [-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small) [-1, 1, Conv, [256, 3, 2]], [[-1, 14], 1, Concat, [1]], # cat head P4 [-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium) [-1, 1, Conv, [512, 3, 2]], [[-1, 10], 1, Concat, [1]], # cat head P5 [-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large) [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ]

对train代码进行如下修改：

parser = argparse.ArgumentParser() parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path') parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml path') parser.add_argument('--data', type=str, default='C:/Users/lindsay/Desktop/yolov5/data/voc2007.yaml', help='data.yaml path') parser.add_argument('--hyp', type=str, default='', help='hyperparameters path, i.e. data/hyp.scratch.yaml') parser.add_argument('--epochs', type=int, default=300) parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs') parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes') parser.add_argument('--rect', action='store_true', help='rectangular training') parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training') parser.add_argument('--nosave', action='store_true', help='only save final checkpoint') parser.add_argument('--notest', action='store_true', help='only test final epoch') parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check') parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters') parser.add_argument('--bucket', type=str, default='', help='gsutil bucket') parser.add_argument('--cache-images', action='store_true', help='cache images for faster training') parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training') parser.add_argument('--name', default='', help='renames results.txt to results_name.txt if supplied') parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%') parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer') parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode') parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify') parser.add_argument('--logdir', type=str, default='runs/', help='logging directory') parser.add_argument('--workers', type=int, default=1, help='maximum number of dataloader workers') opt = parser.parse_args()

改完后直接运行就可以了