TypeError: KittiDataset: __init__() got an unexpected keyword argument 'split'

Question

mmdet上构建kitti数据集，训练时发生错误

Traceback (most recent call last):
  File "tools/train.py", line 255, in <module>
    main()
  File "tools/train.py", line 251, in main
    meta=meta)
  File "/home/shiying/luofan/mmdetection-2.24.0/mmdetection-2.24.0/mmdet/apis/train.py", line 223, in train_detector
    val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
  File "/home/shiying/luofan/mmdetection-2.24.0/mmdetection-2.24.0/mmdet/datasets/builder.py", line 82, in build_dataset
    dataset = build_from_cfg(cfg, DATASETS, default_args)
  File "/home/shiying/zjx/envs/anaconda3/envs/mmlab/lib/python3.7/site-packages/mmcv/utils/registry.py", line 72, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
TypeError: KittiDataset: __init__() got an unexpected keyword argument 'split'

Answer 1

下午好🌅🌅🌅
本答案参考ChatGPT-3.5

问题分析: 在构建KittiDataset数据集时传入了一个split参数，但是KittiDataset的构造函数并没有定义split参数，导致出现TypeError异常。

解决方案:

1. 检查KittiDataset的构造函数参数列表，确保没有定义split参数。
2. 检查调用KittiDataset的地方，确认是否需要传入split参数。如果需要传入split参数，可以考虑修改KittiDataset的构造函数，添加split参数，并相应地修改相关逻辑。

修改后的代码示例:

# 修改KittiDataset的构造函数
class KittiDataset(Dataset):

    def __init__(self, **kwargs):
        # 构造函数的逻辑
        # ...

# 调用KittiDataset时传入split参数
train_dataset = KittiDataset(split='train')