yolo v5 训练自己的数据集
2022年5月18日 家有一亩三分地
准备数据
yolo测试数据集合格式
-
文件夹形式
数据需要包含图像和标签（images&labels）,对应目录需要有训练集和验证集（train&val），test可以没有。标签数据文件名要与图像数据一致，并且在对应的文件夹下。具体显示如下
- XXXX
- images
- train
- val
- labels
- train
- val
- images
-
文本记录方式
xxx
- 标签格式采用txt形式，记录锚点的中心位置，及宽、高。宽高采用归一化后的数据。
准备自己的数据
实验采用 vco-2007数据集合。voc数据集包含了大量的样本及铆框。为了训练方便，假定我们只识别汽车、摩托车和自行车。这时我们就需要手动制作数据集。
-
voc数据集介绍
-
vco数据集的标签在Annotations中，采用xml方式存储的
undefined图像数据在JEPGImages中
undefined类别测试数据在ImageSets中
-
-
自作数据集
参考https://www.it610.com/article/1467270294388432896.htm-
创建数据采用python脚本
import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join import random from shutil import copyfile # 根据自己的数据标签修改 classes=["car", "motorbike", "bicycle"] def clear_hidden_files(path): dir_list = os.listdir(path) for i in dir_list: abspath = os.path.join(os.path.abspath(path), i) if os.path.isfile(abspath): if i.startswith("._"): os.remove(abspath) else: clear_hidden_files(abspath) 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('VOCdevkit/VOC2007/Annotations/%s.xml' %image_id) out_file = open('VOCdevkit/VOC2007/YOLOLabels/%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) i =0 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') i = i+1 in_file.close() out_file.close() return i wd = os.getcwd() wd = os.getcwd() data_base_dir = os.path.join(wd, "VOCdevkit/") if not os.path.isdir(data_base_dir): os.mkdir(data_base_dir) work_sapce_dir = os.path.join(data_base_dir, "VOC2007/") if not os.path.isdir(work_sapce_dir): os.mkdir(work_sapce_dir) annotation_dir = os.path.join(work_sapce_dir, "Annotations/") if not os.path.isdir(annotation_dir): os.mkdir(annotation_dir) clear_hidden_files(annotation_dir) image_dir = os.path.join(work_sapce_dir, "JPEGImages/") if not os.path.isdir(image_dir): os.mkdir(image_dir) clear_hidden_files(image_dir) yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/") if not os.path.isdir(yolo_labels_dir): os.mkdir(yolo_labels_dir) clear_hidden_files(yolo_labels_dir) yolov5_images_dir = os.path.join(data_base_dir, "images/") if not os.path.isdir(yolov5_images_dir): os.mkdir(yolov5_images_dir) clear_hidden_files(yolov5_images_dir) yolov5_labels_dir = os.path.join(data_base_dir, "labels/") if not os.path.isdir(yolov5_labels_dir): os.mkdir(yolov5_labels_dir) clear_hidden_files(yolov5_labels_dir) yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/") if not os.path.isdir(yolov5_images_train_dir): os.mkdir(yolov5_images_train_dir) clear_hidden_files(yolov5_images_train_dir) yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/") if not os.path.isdir(yolov5_images_test_dir): os.mkdir(yolov5_images_test_dir) clear_hidden_files(yolov5_images_test_dir) yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/") if not os.path.isdir(yolov5_labels_train_dir): os.mkdir(yolov5_labels_train_dir) clear_hidden_files(yolov5_labels_train_dir) yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/") if not os.path.isdir(yolov5_labels_test_dir): os.mkdir(yolov5_labels_test_dir) clear_hidden_files(yolov5_labels_test_dir) train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w') test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w') train_file.close() test_file.close() train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a') test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a') list_imgs = os.listdir(image_dir) # list image files probo = random.randint(1, 100) print("Probobility: %d" % probo) for i in range(0,len(list_imgs)): path = os.path.join(image_dir,list_imgs[i]) if os.path.isfile(path): image_path = image_dir + list_imgs[i] voc_path = list_imgs[i] (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path)) (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path)) annotation_name = nameWithoutExtention + '.xml' annotation_path = os.path.join(annotation_dir, annotation_name) label_name = nameWithoutExtention + '.txt' label_path = os.path.join(yolo_labels_dir, label_name) probo = random.randint(1, 100) print("Probobility: %d" % probo) if(probo < 80): # train dataset if os.path.exists(annotation_path): i = convert_annotation(nameWithoutExtention) # convert label if(i>0): train_file.write(yolov5_images_train_dir + voc_path + '\n') copyfile(image_path, yolov5_images_train_dir + voc_path) copyfile(label_path, yolov5_labels_train_dir + label_name) else: # test dataset if os.path.exists(annotation_path): i = convert_annotation(nameWithoutExtention) # convert label if(i>0): test_file.write(yolov5_images_train_dir + voc_path + '\n') copyfile(image_path, yolov5_images_test_dir + voc_path) copyfile(label_path, yolov5_labels_test_dir + label_name) train_file.close() test_file.close()程序将自动创建images和labels文件夹集数据
-
设置yolo 训练yaml文件
在*/yolov5/data/*文件夹下创建一个
myvoc.yaml文件，设置刚刚生成的数据路径# 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: D:/BaiduNetdiskDownload/VOC2007/pascal-voc-2007/VOCdevkit/VOC2007/VOCdevkit # dataset root dir train: images/train # train images (relative to 'path') 118287 images val: images/val # val images (relative to 'path') 5000 images test: images/test # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 # Classes nc: 3 # 修改种类 names: ['car', 'motorbike'， 'bicycle'] # 类别名称 -
修改训练迁移模型及参数
在**/yolov5/models**问价夹下拷贝
yolov5s.yaml更改名称new_train.yaml，并设置样本类别数。根据采用不同的网络需要根据不同的yaml生成测试文件# YOLOv5 🚀 by Ultralytics, GPL-3.0 license # Parameters nc: 3 # 样本类数 depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # layer channel multiple 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
-
训练
执行测试命令
(yolov5-gpu) D:\ptwork\git\yolov5>python train.py --data data\myvoc.yaml --cfg models\new_train.yaml --weights weights\yolov5s.pt --epochs 10 --batch-size 32 --device 0
测试
(yolov5-gpu) D:\ptwork\git\yolov5>python detect.py --weights .\runs\train\exp23\weights\best.pt --source L:\001.jpg --imgsz 5408
detect: weights=['.\\runs\\train\\exp23\\weights\\best.pt'], source=L:\001.jpg, data=data\coco128.yaml, imgsz=[5408, 5408], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs\detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
YOLOv5 v6.1-191-gd29df68 Python-3.9.0 torch-1.10.1 CUDA:0 (NVIDIA GeForce RTX 2080, 8192MiB)
Fusing layers...
new_train summary: 213 layers, 7018216 parameters, 0 gradients
image 1/1 L:\001.jpg: 3680x5408 26 cars, 2 motorbikes, 1 bicycle, Done. (0.153s)
Speed: 29.0ms pre-process, 153.0ms inference, 7.0ms NMS per image at shape (1, 3, 5408, 5408)
Results saved to runs\detect\exp12
在runs\detect\exp12文件夹下查看结果
文章出处登录后可见！
已经登录？立即刷新
