YOLOv11训练时出现'No Labels found in cache'错误的解决求助

嘿，各位大佬！我现在在Google Colab上用YOLOv11训练一个坦克分类模型（一共9个标签），遇到了个棘手的问题，想请大家帮忙排查下~

我从Roboflow上下载了坦克数据集，用的是网站提供的下载代码，数据集的文件夹结构如图所示：

我的初始化代码是这样的：

!mkdir {HOME}/datasets
%cd {HOME}/datasets

from google.colab import userdata
from roboflow import Roboflow

ROBOFLOW_API_KEY = userdata.get('ROBOFLOW_API_KEY')
rf = Roboflow(api_key=ROBOFLOW_API_KEY)

workspace = rf.workspace("liangdianzhong")
project = rf.workspace("capstoneproject").project("russian-military-annotated")
version = project.version(4)
dataset = version.download("yolov11")

接着运行训练命令：

%cd {HOME}

!yolo task=detect mode=train model=yolo11s.pt data={dataset.location}/data.yaml epochs=1 batch=60 imgsz=640 plots=True

结果训练时抛出了警告，最后验证集的指标全为0，错误日志如下：

Transferred 493/499 items from pretrained weights
TensorBoard: Start with 'tensorboard --logdir runs/detect/train7', view at http://localhost:6006/
Freezing layer 'model.23.dfl.conv.weight'
AMP: running Automatic Mixed Precision (AMP) checks...
AMP: checks passed ✅
train: Scanning /content/datasets/Russian-military-annotated-4/train/labels... 1026 images, 33 backgrounds, 0 corrupt: 100% 1026/1026 [00:00<00:00, 1995.16it/s]
train: New cache created: /content/datasets/Russian-military-annotated-4/train/labels.cache
albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))
val: Scanning /content/datasets/Russian-military-annotated-4/valid/labels... 9 images, 9 backgrounds, 0 corrupt: 100% 9/9 [00:00<00:00, 1585.35it/s]
val: New cache created: /content/datasets/Russian-military-annotated-4/valid/labels.cache
WARNING ⚠️ No labels found in /content/datasets/Russian-military-annotated-4/valid/labels.cache, training may not work correctly. See https://docs.ultralytics.com/datasets for dataset formatting guidance.
Plotting labels to runs/detect/train7/labels.jpg... 
optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... 
optimizer: AdamW(lr=0.000714, momentum=0.9) with parameter groups 81 weight(decay=0.0), 88 weight(decay=0.00046875), 87 bias(decay=0.0)
TensorBoard: model graph visualization added ✅
Image sizes 640 train, 640 val
Using 2 dataloader workers
Logging results to runs/detect/train7
Starting training for 1 epochs...

      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
        1/1      15.2G      1.125      5.288      1.594         18        640: 100% 18/18 [00:22<00:00,  1.24s/it]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100% 1/1 [00:00<00:00,  1.50it/s]
                   all          9          0          0          0          0          0
WARNING ⚠️ no labels found in detect set, can not compute metrics without labels

我现在有点懵，不知道为啥验证集找不到标签，训练集明明是正常的。有没有大佬能指点下怎么解决这个问题呀？

备注：内容来源于stack exchange，提问作者myts999