划分VOC数据集，以及转换为划分后的COCO数据集格式

1.VOC数据集

    LabelImg是一款广泛应用于图像标注的开源工具，主要用于构建目标检测模型所需的数据集。Visual Object Classes（VOC）数据集作为一种常见的目标检测数据集，通过labelimg工具在图像中标注边界框和类别标签，为训练模型提供了必要的注解信息。VOC数据集源于对PASCAL挑战赛的贡献，涵盖多个物体类别，成为目标检测领域的重要基准之一，推动着算法性能的不断提升。

    使用labelimg标注或者其他VOC标注工具标注后，会得到两个文件夹，如下:

Annotations    ------->>>  存放.xml标注信息文件
JPEGImages     ------->>>  存放图片文件

2.划分VOC数据集

    如下代码是按照训练集:验证集 = 8:2来划分的，会找出没有对应.xml的图片文件，且划分的时候支持JPEGImages文件夹下有如下图片格式:

['.jpg', '.png', '.gif', '.bmp', '.tiff', '.jpeg', '.webp', '.svg', '.psd', '.cr2', '.nef', '.dng']

整体代码为:

import os
import randomimage_extensions = ['.jpg', '.png', '.gif', '.bmp', '.tiff', '.jpeg', '.webp', '.svg', '.psd', '.cr2', '.nef', '.dng']def split_voc_dataset(dataset_dir, train_ratio, val_ratio):if not (0 < train_ratio + val_ratio <= 1):print("Invalid ratio values. They should sum up to 1.")returnannotations_dir = os.path.join(dataset_dir, 'Annotations')images_dir = os.path.join(dataset_dir, 'JPEGImages')output_dir = os.path.join(dataset_dir, 'ImageSets/Main')if not os.path.exists(output_dir):os.makedirs(output_dir)dict_info = dict()# List all the image files in the JPEGImages directoryfor file in os.listdir(images_dir):if any(ext in file for ext in image_extensions):jpg_files, endwith = os.path.splitext(file)dict_info[jpg_files] = endwith# List all the XML files in the Annotations directoryxml_files = [file for file in os.listdir(annotations_dir) if file.endswith('.xml')]random.shuffle(xml_files)num_samples = len(xml_files)num_train = int(num_samples * train_ratio)num_val = int(num_samples * val_ratio)train_xml_files = xml_files[:num_train]val_xml_files = xml_files[num_train:num_train + num_val]with open(os.path.join(output_dir, 'train_list.txt'), 'w') as train_file:for xml_file in train_xml_files:image_name = os.path.splitext(xml_file)[0]if image_name in dict_info:image_path = os.path.join('JPEGImages', image_name + dict_info[image_name])annotation_path = os.path.join('Annotations', xml_file)train_file.write(f'{image_path} {annotation_path}\n')else:print(f"没有找到图片 {os.path.join(images_dir, image_name)}")with open(os.path.join(output_dir, 'val_list.txt'), 'w') as val_file:for xml_file in val_xml_files:image_name = os.path.splitext(xml_file)[0]if image_name in dict_info:image_path = os.path.join('JPEGImages', image_name + dict_info[image_name])annotation_path = os.path.join('Annotations', xml_file)val_file.write(f'{image_path} {annotation_path}\n')else:print(f"没有找到图片 {os.path.join(images_dir, image_name)}")labels = set()for xml_file in xml_files:annotation_path = os.path.join(annotations_dir, xml_file)with open(annotation_path, 'r') as f:lines = f.readlines()for line in lines:if '<name>' in line:label = line.strip().replace('<name>', '').replace('</name>', '')labels.add(label)with open(os.path.join(output_dir, 'labels.txt'), 'w') as labels_file:for label in labels:labels_file.write(f'{label}\n')if __name__ == "__main__":dataset_dir = 'BirdNest/'train_ratio = 0.8  # Adjust the train-validation split ratio as neededval_ratio = 0.2split_voc_dataset(dataset_dir, train_ratio, val_ratio)

划分好后的截图:

3.VOC转COCO格式

目前很多框架大多支持的是COCO格式，因为存放与使用起来方便，采用了json文件来代替xml文件。

import json
import os
from xml.etree import ElementTree as ETdef parse_xml(dataset_dir, xml_file):xml_path = os.path.join(dataset_dir, xml_file)tree = ET.parse(xml_path)root = tree.getroot()objects = root.findall('object')annotations = []for obj in objects:bbox = obj.find('bndbox')xmin = int(bbox.find('xmin').text)ymin = int(bbox.find('ymin').text)xmax = int(bbox.find('xmax').text)ymax = int(bbox.find('ymax').text)# Extract label from XML annotationlabel = obj.find('name').textif not label:print(f"Label not found in XML annotation. Skipping annotation.")continueannotations.append({'xmin': xmin,'ymin': ymin,'xmax': xmax,'ymax': ymax,'label': label})return annotationsdef convert_to_coco_format(image_list_file, annotations_dir, output_json_file, dataset_dir):images = []annotations = []categories = []# Load labelswith open(os.path.join(os.path.dirname(image_list_file), 'labels.txt'), 'r') as labels_file:label_lines = labels_file.readlines()categories = [{'id': i + 1, 'name': label.strip()} for i, label in enumerate(label_lines)]# Load image list filewith open(image_list_file, 'r') as image_list:image_lines = image_list.readlines()for i, line in enumerate(image_lines):image_path, annotation_path = line.strip().split(' ')image_id = i + 1image_filename = os.path.basename(image_path)# Extract image size from XML filexml_path = os.path.join(dataset_dir, annotation_path)tree = ET.parse(xml_path)size = tree.find('size')image_height = int(size.find('height').text)image_width = int(size.find('width').text)images.append({'id': image_id,'file_name': image_filename,'height': image_height,'width': image_width,'license': None,'flickr_url': None,'coco_url': None,'date_captured': None})# Load annotations from XML filesxml_annotations = parse_xml(dataset_dir, annotation_path)for xml_annotation in xml_annotations:label = xml_annotation['label']category_id = next((cat['id'] for cat in categories if cat['name'] == label), None)if category_id is None:print(f"Label '{label}' not found in categories. Skipping annotation.")continuebbox = {'xmin': xml_annotation['xmin'],'ymin': xml_annotation['ymin'],'xmax': xml_annotation['xmax'],'ymax': xml_annotation['ymax']}annotations.append({'id': len(annotations) + 1,'image_id': image_id,'category_id': category_id,'bbox': [bbox['xmin'], bbox['ymin'], bbox['xmax'] - bbox['xmin'], bbox['ymax'] - bbox['ymin']],'area': (bbox['xmax'] - bbox['xmin']) * (bbox['ymax'] - bbox['ymin']),'segmentation': [],'iscrowd': 0})coco_data = {'images': images,'annotations': annotations,'categories': categories}with open(output_json_file, 'w') as json_file:json.dump(coco_data, json_file, indent=4)if __name__ == "__main__":# 根据需要调整路径dataset_dir = 'BirdNest/'image_sets_dir = 'BirdNest/ImageSets/Main/'train_list_file = os.path.join(image_sets_dir, 'train_list.txt')val_list_file = os.path.join(image_sets_dir, 'val_list.txt')output_train_json_file = os.path.join(dataset_dir, 'train_coco.json')output_val_json_file = os.path.join(dataset_dir, 'val_coco.json')convert_to_coco_format(train_list_file, image_sets_dir, output_train_json_file, dataset_dir)convert_to_coco_format(val_list_file, image_sets_dir, output_val_json_file, dataset_dir)print("The json file has been successfully generated!!!")

转COCO格式成功截图: