yolov8 训练自己的数据集

1，准备数据集

1.1voc数据转yolo数据

voc格式

文件联级如下所述：
VOCdevkit
    ---VOC2007
        ---Annotations
        ---ImageSets
        ---JPEGImages

yolo格式

voc_to_yolo.py

from tqdm import tqdm
import shutil
from pathlib import Path
import xml.etree.ElementTree as ET

def convert_label(path, lb_path, year, image_id, names):
    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 names:
            xmlbox = obj.find('bndbox')
            bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
            cls_id = names.index(cls)  # class id
            out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + '\n')
        else:
            print("category error: ", cls)

year = "2007"
image_sets = ["train", "val"]
path = Path("H:\\work\\daodan_move\\ultralytics-main\\ultralytics\\datasets\\VOCdevkit\\")
class_names = ["call","dislike","fist","four","like","mute","ok","one","palm","1","2","3","4","5","6","7","8","9","10"]

for image_set in image_sets:
    imgs_path = path / 'images' / f'{image_set}'
    lbs_path = path / 'labels' / f'{image_set}'
    imgs_path.mkdir(exist_ok=True, parents=True)
    lbs_path.mkdir(exist_ok=True, parents=True)
    
    with open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt') as f:
        image_ids = f.read().strip().split()
    for id in tqdm(image_ids, desc=f'{image_set}'):
        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
        shutil.copyfile(f, imgs_path / f.name) # copy image
        convert_label(path, lb_path, year, id, class_names)  # convert labels to YOLO format

1.2 COCO格式转YOLO格式 转换脚本

coco格式

── VOCdevkit
├── images
│   ├── train	# 存放训练集图片
│   └── val	# 存放验证集图片
└── labels
    ├── train	# 存放训练集标注文件
    └── val	# 存放验证集标注文件

import json
import os
import shutil
from tqdm import tqdm

coco_path = "F:/datasets/Apple_Detection_Swift-YOLO_192"
output_path = "F:/vsCode/ultralytics/datasets/Apple"

os.makedirs(os.path.join(output_path, "images", "train"), exist_ok=True)
os.makedirs(os.path.join(output_path, "images", "val"), exist_ok=True)
os.makedirs(os.path.join(output_path, "labels", "train"), exist_ok=True)
os.makedirs(os.path.join(output_path, "labels", "val"), exist_ok=True)

with open(os.path.join(coco_path, "train", "_annotations.coco.json"), "r") as f:
    train_annotations = json.load(f)

with open(os.path.join(coco_path, "valid", "_annotations.coco.json"), "r") as f:
    val_annotations = json.load(f)
    
# Iterate over the training images
for image in tqdm(train_annotations["images"]):
    width, height = image["width"], image["height"]
    scale_x = 1.0 / width
    scale_y = 1.0 / height
    
    label = ""
    for annotation in train_annotations["annotations"]:
        if annotation["image_id"] == image["id"]:
            # Convert the annotation to YOLO format
            x, y, w, h = annotation["bbox"]
            x_center = x + w / 2.0
            y_center = y + h / 2.0
            x_center *= scale_x
            y_center *= scale_y
            w *= scale_x
            h *= scale_y
            class_id = annotation["category_id"]
            label += "{} {} {} {} {}\n".format(class_id, x_center, y_center, w, h)
            
    # Save the image and label
    shutil.copy(os.path.join(coco_path, "train", image["file_name"]), os.path.join(output_path, "images", "train", image["file_name"]))
    with open(os.path.join(output_path, "labels", "train", image["file_name"].replace(".jpg", ".txt")), "w") as f:
        f.write(label)
        
# Iterate over the validation images
for image in tqdm(val_annotations["images"]):
    width, height = image["width"], image["height"]
    scale_x = 1.0 / width
    scale_y = 1.0 / height
    
    label = ""
    for annotation in val_annotations["annotations"]:
        if annotation["image_id"] == image["id"]:
            # Convert the annotation to YOLO format
            x, y, w, h = annotation["bbox"]
            x_center = x + w / 2.0
            y_center = y + h / 2.0
            x_center *= scale_x
            y_center *= scale_y
            w *= scale_x
            h *= scale_y
            class_id = annotation["category_id"]
            label += "{} {} {} {} {}\n".format(class_id, x_center, y_center, w, h)
            
    # Save the image and label
    shutil.copy(os.path.join(coco_path, "valid", image["file_name"]), os.path.join(output_path, "images", "val", image["file_name"]))
    with open(os.path.join(output_path, "labels", "val", image["file_name"].replace(".jpg", ".txt")), "w") as f:
        f.write(label)

2.训练数据

将voc.yaml复制为voc_self.yaml,然后修改如下：

# Ultralytics YOLO 🚀, AGPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Documentation: # Documentation: https://docs.ultralytics.com/datasets/detect/voc/
# Example usage: yolo train data=VOC.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── VOC  ← downloads here (2.8 GB)

# 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: H:\\work\\daodan_move\\ultralytics-main\\ultralytics\\datasets\\VOCdevkit
train: # train images (relative to 'path')  16551 images
  - images/train
val: # val images (relative to 'path')  4952 images
  - images/val
test: # test images (optional)
  - images/val

# Classes
names:
  0: call
  1: dislike
  2: fist
  3: four
  4: like
  5: mute
  6: ok
  7: one
  8: palm
  9: 1
  10: 2
  11: 3
  12: 4
  13: 5
  14: 6
  15: 7
  16: 8
  17: 9
  18: 10

训练数据

yolo task=detect mode=train model=yolov8n.pt data=H:\\work\\daodan_move\\ultralytics-main\\ultralytics\\cfg\\datasets\\VOC_self.yaml epochs=100 batch=4 device=0

or

# from ultralytics import YOLO

# # Load a model
# model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)

# # Train the model with 2 GPUs
# results = model.train(data="H:\\work\\daodan_move\\ultralytics-main\\ultralytics\\cfg\\datasets\\VOC_self.yaml", epochs=100, imgsz=640, device="0")

from ultralytics import YOLO
if __name__ == '__main__':
    #下面是三种训练的方式，使用其中一个的时候要注释掉另外两个
    # Load a model  加载模型
    #这种方式是选择.yaml模型文件，从零开始训练
    # model = YOLO('yolov8n.yaml')  # build a new model from YAML
    #这种方式是选择.pt文件，利用预训练模型训练
    model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)
    #这种方式是可以加载自己想要使用的预训练模型
    # model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights
    
    # Train the model   data = 这里用来设置你的data.yaml路径。即第一步设置的文件。后面的就是它的一些属性设置，你也可以增加一些比如batch=16等等。
    model.train(data='H:\\work\\daodan_move\\ultralytics-main\\ultralytics\\cfg\\datasets\\VOC_self.yaml', epochs=100, imgsz=640, device="0")