使用目标检测yolov8去训练显微镜下浮游藻类生物检测数据集VOC+YOLO格式16239张80类别步骤和流程

import os
import shutil
import random


class VOCDataSplit(object):
    def __init__(self):
        pass

    def split(self, image_dir, label_dir, save_dir, trainval_radio=0.9, train_radio=0.9, copy_it=True,
              need_test_dataset=False, shuffle_file=True):
        train_images_dir = os.path.join(save_dir, 'train', 'images')
        train_labels_dir = os.path.join(save_dir, 'train', 'labels')
        val_images_dir = os.path.join(save_dir, 'val', 'images')
        val_labels_dir = os.path.join(save_dir, 'val', 'labels')
        test_images_dir = os.path.join(save_dir, 'test', 'images')
        test_labels_dir = os.path.join(save_dir, 'test', 'labels')
        os.makedirs(train_images_dir, exist_ok=True)
        os.makedirs(train_labels_dir, exist_ok=True)
        os.makedirs(val_images_dir, exist_ok=True)
        os.makedirs(val_labels_dir, exist_ok=True)
        if need_test_dataset:
            os.makedirs(test_images_dir, exist_ok=True)
            os.makedirs(test_labels_dir, exist_ok=True)
        files = []
        for file in os.listdir(image_dir):
            if file.endswith('.jpg'):
                files.append(file)
        total_count = len(files)
        print('find {} images'.format(total_count))
        if shuffle_file:
            random.shuffle(files)
        if need_test_dataset:
            test_count = int(total_count * (1 - trainval_radio))
            train_count = int((total_count - test_count) * train_radio)
            val_count = total_count - test_count - train_count
        else:
            train_count = int(total_count * train_radio)
            val_count = total_count - train_count
            test_count = 0
        print('train={},val={},test={}'.format(train_count, val_count, test_count))

        train_files = files[:train_count]
        val_files = files[train_count:train_count + val_count]
        test_files = files[train_count + val_count:]
        print('start copy or move train files...')
        for file in train_files:
            if copy_it:
                shutil.copy(os.path.join(image_dir, file), os.path.join(train_images_dir, file))
                label_file = os.path.join(label_dir, file[:-3] + 'txt')
                if os.path.exists(label_file):
                    shutil.copy(label_file, os.path.join(train_labels_dir, file[:-3] + 'txt'))
            else:
                shutil.move(os.path.join(image_dir, file), os.path.join(train_images_dir, file))
                label_file = os.path.join(label_dir, file[:-3] + 'txt')
                if os.path.exists(label_file):
                    shutil.move(label_file, os.path.join(train_labels_dir, file[:-3] + 'txt'))

        print('start copy or move val files...')
        for file in val_files:
            if copy_it:
                shutil.copy(os.path.join(image_dir, file), os.path.join(val_images_dir, file))
                label_file = os.path.join(label_dir, file[:-3] + 'txt')
                if os.path.exists(label_file):
                    shutil.copy(label_file, os.path.join(val_labels_dir, file[:-3] + 'txt'))
            else:
                shutil.move(os.path.join(image_dir, file), os.path.join(val_images_dir, file))
                label_file = os.path.join(label_dir, file[:-3] + 'txt')
                if os.path.exists(label_file):
                    shutil.move(label_file, os.path.join(val_labels_dir, file[:-3] + 'txt'))

        if need_test_dataset and test_count > 0:
            print('start copy or move test files...')
            for file in test_files:
                if copy_it:
                    shutil.copy(os.path.join(image_dir, file), os.path.join(test_images_dir, file))
                    label_file = os.path.join(label_dir, file[:-3] + 'txt')
                    if os.path.exists(label_file):
                        shutil.copy(label_file, os.path.join(test_labels_dir, file[:-3] + 'txt'))
                else:
                    shutil.move(os.path.join(image_dir, file), os.path.join(test_images_dir, file))
                    label_file = os.path.join(label_dir, file[:-3] + 'txt')
                    if os.path.exists(label_file):
                        shutil.move(label_file, os.path.join(test_labels_dir, file[:-3] + 'txt'))

        class_file=os.path.join(label_dir, 'classes.txt')
        if os.path.exists(class_file):
            class_names=[]
            with open(class_file, 'r') as f:
                class_names=f.read().rstrip('\n').split('\n')
            nc = len(class_names)
            content='train: '+train_images_dir+'\n'
            content += 'val: '+val_images_dir+'\n'
            if need_test_dataset:
                content += 'test: '+test_images_dir+'\n'
            content += 'nc: '+str(nc)+'\n'
            content += 'names:\n'
            content += "\n".join([f"  {i}: {name}" for i, name in enumerate(class_names)])
            with open(os.path.join(save_dir,'coco128.yaml'), 'w') as f:
                f.write(content)
        print('all done!')
if __name__ == '__main__':
    images_dir=r'C:\Users\Administrator\Downloads\data\JPEGImages'
    labels_dir=r'C:\Users\Administrator\Downloads\data\labels'
    save_dir=r'C:\Users\Administrator\Downloads\dataset'
    vs = VOCDataSplit()
    vs.split(images_dir,labels_dir,save_dir,trainval_radio=0.9, train_radio=0.9, copy_it=True,shuffle_file=True,need_test_dataset=False)

train: C:\Users\Administrator\Downloads\dataset\train\images
val: C:\Users\Administrator\Downloads\dataset\val\images
nc: 3
names:
  0: class_name1
  1: class_name2
  2: class_name3

from ultralytics import YOLO

# 加载训练好的模型
model = YOLO('runs/detect/train/weights/best.pt')

# 图像预测
results = model('path_to_your_image.jpg')

results = model('path_to_video.mp4')  # 视频
#results = model(0)  # 摄像头

yolo task=detect mode=val model=runs/detect/train/weights/best.pt data=data.yaml