v8目标检测

1.将数据集分为训练集和验证集

 dataset/
   ├── train/
       ├── images/

       └── labels/
  └── val/
       ├── images/
       └── labels/

import os
import shutil
import random

random.seed(0)


def split_data(file_path,xml_path, new_file_path1, new_file_path2, train_rate, val_rate, test_rate):
    each_class_image = []
    each_class_label = []
    for image in os.listdir(file_path):
        each_class_image.append(image)
    for label in os.listdir(xml_path):
        each_class_label.append(label)
    data=list(zip(each_class_image,each_class_label))
    total = len(each_class_image)
    random.shuffle(data)
    each_class_image,each_class_label=zip(*data)
    train_images = each_class_image[0:int(train_rate * total)]
    val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_images = each_class_image[int((train_rate + val_rate) * total):]
    train_labels = each_class_label[0:int(train_rate * total)]
    val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_labels = each_class_label[int((train_rate + val_rate) * total):]

    for image in train_images:
        print(image)
        old_path = file_path + '/' + image
        new_path1 = new_file_path1 + '/' + 'train' 
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in train_labels:
        print(label)
        old_path = xml_path + '/' + label
        new_path1 = new_file_path2 + '/' + 'train' 
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)


    for image in test_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path1 + '/' + 'val' 
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in test_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path2 + '/' + 'val'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)


if __name__ == '__main__':
    file_path = "D:/desktop/picture"
    xml_path = 'D:/desktop/label 2'
    new_file_path1 = "D:/desktop/datasets/images"
    new_file_path2 = "D:/desktop/datasets/labels"
    split_data(file_path,xml_path, new_file_path1, new_file_path2, train_rate=0.8, val_rate=0.0, test_rate=0.2)

2.yaml文件

train: #绝对路径
val: 

# number of classes
nc: 7

# class names
names: ["comet-T", "comet","steak","w","ww","head","impurity"]

3.先测试一下

yolo predict model=yolov8n.pt source="/share/home/zju_jiangyy/comet/cometv8/bus.jpg" save= True

4. train.py

from ultralytics import YOLO

# Load a model

model = YOLO("yolov8m.pt")  # load a pretrained model (recommended for training)
model = YOLO("yolov8m.yaml").load("yolov8m.pt")  # build from YAML and transfer weights

# Train the model
results = model.train(data="..../.yaml", epochs=300)

5.练完在照片上试试

yolo detect predict model=/share...runs/detect/train5/weights/best.pt 
source=/share.../test1 save=True

6.怎么知道模型是否可以提升或者是训练效果好不好呢？