You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
TypeError: bbox_head={'num_classes': 1} in child config cannot inherit from base because bbox_head is a dict in the child config but is of type <class 'list'> in base config. You may set _delete_=True to ignore the base config
#76
Open
AngSoonKim opened this issue
Dec 14, 2020
· 0 comments
Hi wanted to ask if you met this error when training Detectors and how was it resolved in the end?
This error occurs when you try to train a Detectors model on a customized data-sets using mmdetection using similar process as other model.
Traceback (most recent call last):
File "tools/Train_ForDetectors.py", line 142, in <module>
main()
File "tools/Train_ForDetectors.py", line 61, in main
cfg = Config.fromfile(args.config)
File "/home/adotesdotekdote/miniconda3/lib/python3.8/site-packages/mmcv/utils/config.py", line 215, in fromfile
cfg_dict, cfg_text = Config._file2dict(filename,
File "/home/adotesdotekdote/miniconda3/lib/python3.8/site-packages/mmcv/utils/config.py", line 183, in _file2dict
base_cfg_dict = Config._merge_a_into_b(cfg_dict, base_cfg_dict)
File "/home/adotesdotekdote/miniconda3/lib/python3.8/site-packages/mmcv/utils/config.py", line 206, in _merge_a_into_b
b[k] = Config._merge_a_into_b(v, b[k])
File "/home/adotesdotekdote/miniconda3/lib/python3.8/site-packages/mmcv/utils/config.py", line 206, in _merge_a_into_b
b[k] = Config._merge_a_into_b(v, b[k])
File "/home/adotesdotekdote/miniconda3/lib/python3.8/site-packages/mmcv/utils/config.py", line 201, in _merge_a_into_b
raise TypeError(
TypeError: bbox_head={'num_classes': 1} in child config cannot inherit from base because bbox_head is a dict in the child config but is of type <class 'list'> in base config. You may set `_delete_=True` to ignore the base config
The text was updated successfully, but these errors were encountered:
Hi wanted to ask if you met this error when training Detectors and how was it resolved in the end?
This error occurs when you try to train a Detectors model on a customized data-sets using mmdetection using similar process as other model.
The text was updated successfully, but these errors were encountered: