Google colab 在 <path>

Question

我正在尝试训练YOLOV8目标检测模型。我已经导入了所有必需的库，并成功安装了谷歌驱动器并获得了我需要的文件夹。

请注意，我在 github 和 stackoverflow 上看到了很多关于同一问题的帖子，但没有任何效果对我有用。

这就是我的结构查找图像和标签的方式：

这是获取库和训练模型的代码：

!pip install ultralytics
!pip install Ipython


#Install YOLOV8 libraries
from IPython import display
display.clear_output()

import ultralytics
ultralytics.checks()

#Mount the drive
from google.colab import drive
drive.mount('/content/drive')


#Babesia dataset 1
%cd /content/drive/MyDrive/Babesia - dataset2
from ultralytics import YOLO

#Use pre-trained model
!yolo task=detect mode=train model=yolov8s.pt data=data.yaml epochs =2 plots=True

这是我的 data.yaml 文件：

train: /content/drive/MyDrive/Babesia - dataset2/Data/images/train/trainImages
val: /content/drive/MyDrive/Babesia - dataset2/Data/images/valid/validImages

nc: 1
names: ['Babesiidae']

这是我得到的错误：

train: Scanning /content/drive/MyDrive/Babesia - dataset2/Data/labels/train/trainImages... 0 images, 457 backgrounds, 0 corrupt: 100% 457/457 [00:11<00:00, 41.26it/s] 
train: WARNING ⚠️ No labels found in /content/drive/MyDrive/Babesia - dataset2/Data/labels/train/trainImages.cache. See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance.
train: New cache created: /content/drive/MyDrive/Babesia - dataset2/Data/labels/train/trainImages.cache
WARNING ⚠️ No labels found in /content/drive/MyDrive/Babesia - dataset2/Data/labels/train/trainImages.cache, training may not work correctly. See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance.
albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))
val: Scanning /content/drive/MyDrive/Babesia - dataset2/Data/labels/valid/validImages... 0 images, 57 backgrounds, 0 corrupt: 100% 57/57 [00:15<00:00,  3.62it/s]
val: WARNING ⚠️ No labels found in /content/drive/MyDrive/Babesia - dataset2/Data/labels/valid/validImages.cache. See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance.
val: WARNING ⚠️ Cache directory /content/drive/MyDrive/Babesia - dataset2/Data/labels/valid is not writeable, cache not saved.
WARNING ⚠️ No labels found in /content/drive/MyDrive/Babesia - dataset2/Data/labels/valid/validImages.cache, training may not work correctly. See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance.
Plotting labels to runs/detect/train/labels.jpg... 
zero-size array to reduction operation maximum which has no identity

如上所述，我检查了许多其他帖子以尝试解决该问题。我还尝试通过将标签与各自的图像文件夹一起更改文件夹结构，这是其他帖子所建议的，但它会产生相同的错误。

Answer 1

你解决了吗？我收到这个错误。我解决不了。 “警告⚠️在检测集中找不到标签，无法计算没有标签的指标”。我仍在寻找解决这个问题的方法。