I made the following modifications to _base_ in config.py to expect to train on the VOC dataset:
_base_ = [
'mmdet::_base_/datasets/voc0712.py',
'mmdet::_base_/schedules/schedule1x.py',
'mmdet::_base\/default_runtime.py'
]
However, the code reports the following error:
TypeError: class IterBasedTrainLoop in mmengine/runner/loops.py: class RepeatDataset in mmengine/dataset/dataset_wrapper.py: init() got an unexpected keyword argument 'filter_cfg'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2728403) of binary: /home/anaconda3/envs/mm3/bin/python
try checking the parameters fed to mmdet/datasets/builder:build_dataset. In your case, it seems to return a RepeatDataset class that doesn't have a parameter named filter_cfg in its __init__()
I made the following modifications to _base_ in config.py to expect to train on the VOC dataset: _base_ = [ 'mmdet::_base_/datasets/voc0712.py', 'mmdet::_base_/schedules/schedule1x.py', 'mmdet::_base\/default_runtime.py' ] However, the code reports the following error: TypeError: class
IterBasedTrainLoop
in mmengine/runner/loops.py: classRepeatDataset
in mmengine/dataset/dataset_wrapper.py: init() got an unexpected keyword argument 'filter_cfg' ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 2728403) of binary: /home/anaconda3/envs/mm3/bin/pythonHow should I fix it? thanks