-
Notifications
You must be signed in to change notification settings - Fork 2.8k
Description
Describe the feature
Motivation
A clear and concise description of the motivation of the feature.
Ex1. I want to to use init_model function generically to call all the segmentor models.
init_model(config_file, checkpoint_file, device='cuda:0')
However I am facing issue while doing that it says
Traceback (most recent call last):
File "/home/akshay/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/config/config.py", line 107, in getattr
value = super().getattr(name)
File "/home/akshay/anaconda3/envs/openmmlab/lib/python3.8/site-packages/addict/addict.py", line 67, in getattr
return self.getitem(item)
File "/home/akshay/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/config/config.py", line 136, in getitem
return self.build_lazy(super().getitem(key))
File "/home/akshay/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/config/config.py", line 103, in missing
raise KeyError(name)
KeyError: 'backbone'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "just_testing_mmseg_san.py", line 10, in
segmentor_model = init_model(config_file, checkpoint_file, device='cuda:0')
File "/home/akshay/work/colorformer_allcode/ColorFormer_SegFormer/mmsegmentation/mmseg/apis/inference.py", line 47, in init_model
elif 'init_cfg' in config.model.backbone:
File "/home/akshay/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/config/config.py", line 111, in getattr
raise AttributeError(f"'{self.class.name}' object has no "
AttributeError: 'ConfigDict' object has no attribute 'backbone'