YOLOv8-训练train.py参数设置

m0_56843848

已于 2024-06-29 16:58:44 修改

阅读量855

点赞数 4

CC 4.0 BY-SA版权

文章标签：人工智能 YOLO python

于 2024-06-29 15:43:54 首次发布

本文链接：https://blog.csdn.net/m0_56843848/article/details/140065178

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
 
if __name__ == '__main__':
    model = YOLO('ultralytics/cfg/models/v8/yolov8n.yaml')
    # model.load('yolov8n.pt') # loading pretrain weights
 
    # # model = YOLO('yolov8n.yaml')  # build a new model from YAML
    # model = YOLO('runs/detect/train_v8n/exp_v8n-eyeball5/weights/last.pt')  # load a pretrained model (recommended for training),配合resume=True,
    # # model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights
    # model = all('ultralytics/cfg/models/v8/my-yolov8-CBAM-b1.yaml')  # 从头开始构建新模型
 
    model.train(data='./datasets/DYC/dataYAWDD.yaml',
    # model.train(data='/home/hjj/Desktop/dataset/dataset_visdrone/data_exp.yaml',
    # model.train(data='F/yolo/bilibilimodao/YOLOv8/ultralytics-20240627/ultralytics-main/datasets/DYC/dataYAWDD.yaml',
                # data=r'coco128.yaml',
                cache=False,  # (bool) True/ram、磁盘或False。使用缓存加载数据