从昆虫识别项目出来，把数据集换成自己拍摄的照片，107张照片。用labelme标注后上传AI studio作为自己的数据集。后来又把labels.txt等相关文件做好了放进数据集目录。跑到设置数据集时出错，最后一句不明白出错在哪。感觉是labels.txt和其他几个文件的问题。因为相同的数据集在paddleX上在本地跑完了没问题。

train_dataset = pdx.datasets.VOCDetection(
    data_dir='dataset_voc',
    file_list='dataset_voc/train_list.txt',
    label_list='dataset_voc/labels.txt',
    transforms=train_transforms,
    shuffle=True)
eval_dataset = pdx.datasets.VOCDetection(
    data_dir='dataset_voc',
    file_list='dataset_voc/val_list.txt',
    label_list='dataset_voc/labels.txt',
    transforms=eval_transforms)

出错信息：

2021-05-17 20:59:58 [INFO] Starting to read file list from dataset...

---------------------------------------------------------------------------ValueError Traceback (most recent call last) in
4 label_list='dataset_voc/labels.txt',
5 transforms=train_transforms,
----> 6 shuffle=True)
7 eval_dataset = pdx.datasets.VOCDetection(
8 data_dir='dataset_voc',
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlex/cv/datasets/voc.py in __init__(self, data_dir, file_list, label_list, transforms, num_workers, buffer_size, parallel_method, shuffle)
102 .format(line))
103 img_file, xml_file = [osp.join(data_dir, x) \
--> 104 for x in line.strip().split()[:2]]
105 img_file = path_normalization(img_file)
106 xml_file = path_normalization(xml_file)
ValueError: not enough values to unpack (expected 2, got 0)