【YOLOV5-6.1 源码注释】VOC.yaml

最新推荐文章于 2023-08-14 20:23:02 发布

keys_7

最新推荐文章于 2023-08-14 20:23:02 发布

阅读量925

点赞数

文章标签：目标检测深度学习人工智能

本文链接：https://blog.csdn.net/weixin_42911918/article/details/126134553

版权

前言

源码： YOLOv5源码.
链接: 【YOLOV5-6.1 源码注释】整体项目文件导航.
注释版全部项目文件已上传至GitHub: yolov5-6.1-annotations.

配置文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Example usage: python train.py --data VOC.yaml
# parent
# ├── yolov5
# └── datasets
#     └── VOC  ← downloads here


# 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: ../datasets/VOC
train: # train images (relative to 'path')  16551 images
  - images/train2012
  - images/train2007
  - images/val2012
  - images/val2007
val: # val images (relative to 'path')  4952 images
  - images/test2007
test: # test images (optional)
  - images/test2007

# Classes
nc: 20  # number of classes
names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
        'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']  # class names


# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  import xml.etree.ElementTree as ET

  from tqdm import tqdm
  from utils.general import download, Path


  def convert_label(path, lb_path, year, image_id):
      def convert_box(size, box):
          dw, dh = 1. / size[0], 1. / size[1]
          x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
          return x * dw, y * dh, w * dw, h * dh

      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
      out_file = open(lb_path, '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'):
          cls = obj.find('name').text
          if cls in yaml['names'] and not int(obj.find('difficult').text) == 1:
              xmlbox = obj.find('bndbox')
              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
              cls_id = yaml['names'].index(cls)  # class id
              out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n')


  # Download
  dir = Path(yaml['path'])  # dataset root dir
  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
  urls = [url + 'VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
          url + 'VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
          url + 'VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
  download(urls, dir=dir / 'images', delete=False)

  # Convert
  path = dir / f'images/VOCdevkit'
  for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
      imgs_path = dir / 'images' / f'{image_set}{year}'
      lbs_path = dir / 'labels' / f'{image_set}{year}'
      imgs_path.mkdir(exist_ok=True, parents=True)
      lbs_path.mkdir(exist_ok=True, parents=True)

      image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split()
      for id in tqdm(image_ids, desc=f'{image_set}{year}'):
          f = path / f'VOC{year}/JPEGImages/{id}.jpg'  # old img path
          lb_path = (lbs_path / f.name).with_suffix('.txt')  # new label path
          f.rename(imgs_path / f.name)  # move image
          convert_label(path, lb_path, year, id)  # convert labels to YOLO format

注释

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Example usage: python train.py --data VOC.yaml
# parent
# ├── yolov5
# └── datasets
#     └── VOC  ← downloads here

# ====================== 数据集源路径root、训练集、验证集、测试集地址 ===================== #
path: ../datasets/VOC   # 数据集源路径root dir
train: # root下的训练集地址  16551 images
  - images/train2012
  - images/train2007
  - images/val2012
  - images/val2007
val: # root下的验证集地址  4952 images
  - images/test2007
test: # root下的验证集地址 (optional)
  - images/test2007

# ================================== 数据集类别信息 ================================== #
# Classes
nc: 20  # 数据集类别数量
names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
        'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']  # 数据集类别名


# ==================================== 数据集下载 ===================================== #
# Download script/URL (optional) ---------------------------------------------------------------------------------------
#download: |
#  import xml.etree.ElementTree as ET
#
#  from tqdm import tqdm
#  from utils.general import download, Path
#
#
#  def convert_label(path, lb_path, year, image_id):
#      def convert_box(size, box):
#          dw, dh = 1. / size[0], 1. / size[1]
#          x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
#          return x * dw, y * dh, w * dw, h * dh
#
#      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
#      out_file = open(lb_path, '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'):
#          cls = obj.find('name').text
#          if cls in yaml['names'] and not int(obj.find('difficult').text) == 1:
#              xmlbox = obj.find('bndbox')
#              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
#              cls_id = yaml['names'].index(cls)  # class id
#              out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n')
#
#
#  # Download
#  dir = Path(yaml['path'])  # dataset root dir
#  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
#  urls = [url + 'VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
#          url + 'VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
#          url + 'VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
#  download(urls, dir=dir / 'images', delete=False)
#
#  # Convert
#  path = dir / f'images/VOCdevkit'
#  for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
#      imgs_path = dir / 'images' / f'{image_set}{year}'
#      lbs_path = dir / 'labels' / f'{image_set}{year}'
#      imgs_path.mkdir(exist_ok=True, parents=True)
#      lbs_path.mkdir(exist_ok=True, parents=True)
#
#      image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split()
#      for id in tqdm(image_ids, desc=f'{image_set}{year}'):
#          f = path / f'VOC{year}/JPEGImages/{id}.jpg'  # old img path
#          lb_path = (lbs_path / f.name).with_suffix('.txt')  # new label path
#          f.rename(imgs_path / f.name)  # move image
#          convert_label(path, lb_path, year, id)  # convert labels to YOLO format