YOLOv7训练自己的VOC数据集_RooKiChen_voc数据集 yolo

网络 02-07 5942

YOLOv7源码：https://github.com/WongKinYiu/yolov7

本文是对YOLOV7训练自己的yolo数据集的扩展，具体训练等步骤不再详细赘述，遇到看不懂的请移步YOLOV7训练自己的yolo数据集。

文章目录一、配置YOLOv7环境二、使用自己的数据集进行训练VOC数据集格式VOC数据集转换为yolo格式修改YOLOv7配置

一、配置YOLOv7环境

参考YOLOV7训练自己的yolo数据集

二、使用自己的数据集进行训练 VOC数据集格式

正常的VOC格式

VOC数据集转换为yolo格式

可以参考我这篇博客的内容：将VOC数据集转换为yolo格式，也可以直接复制下面的代码（更方便）。

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 # 填入自己voc数据集类别 classes = ["side_head","back_head"] # 训练集和验证集的比例 TRAIN_RATIO = 0.5 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('/home/wu_datasets/yolov7-main/VOCdevkit/VOC2012/Annotations/%s.xml' % image_id) out_file = open('/home/wu_datasets/yolov7-main/VOCdevkit/VOC2012/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) for obj in root.iter('object'): # difficult = obj.find('difficult').text cls = obj.find('name').text if cls not in classes: 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') in_file.close() out_file.close() 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, "VOC2012/") 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, "yolov7_train.txt"), 'w') test_file = open(os.path.join(wd, "yolov7_val.txt"), 'w') train_file.close() test_file.close() train_file = open(os.path.join(wd, "yolov7_train.txt"), 'a') test_file = open(os.path.join(wd, "yolov7_val.txt"), 'a') list_imgs = os.listdir(image_dir) # list image files prob = random.randint(1, 100) print("Probability: %d" % prob) 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) prob = random.randint(1, 100) print("Probability: %d" % prob) if (prob < int(TRAIN_RATIO * 100)): # train dataset if os.path.exists(annotation_path): train_file.write(image_path + '\n') convert_annotation(nameWithoutExtention) # convert label 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): test_file.write(image_path + '\n') convert_annotation(nameWithoutExtention) # convert label copyfile(image_path, yolov5_images_test_dir + voc_path) copyfile(label_path, yolov5_labels_test_dir + label_name) train_file.close() test_file.close() 在yolov7目录下新建voc2yolo.py文件，复制上面的代码，更改类别标签和xml路径即可。

运行voc2yolo.py文件

修改YOLOv7配置

请参考YOLOV7训练自己的yolo数据集，这里只说明如何使用VOC训练

新建voc.yaml文件

把生成的两个文件yolov7_train.txt和yolov7_val.txt放入路径中，就可以开始训练了训练请参考YOLOV7训练自己的yolo数据集