How to solve the unregistry bug during training process?

[kylechang523]

Hi,

I want to re-implement the training pipeline and follow the README, but while loading the model I found this bug:

KeyError: "No object named 'SOTR' found in 'META_ARCH' registry!"

May I ask how to solve it?

[nlpkiddo-2001]

+1, Awesome work. Can you share an example script for sample usage. It would be very helpful

`from detectron2.config import get_cfg
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor

from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog

config = get_cfg()

config.merge_from_file('/DocSegTr/configs/SOTR/R_101_DCN_doc.yaml')
config.MODEL.WEIGHTS = 'document_image_segmentation/model_final_prima_docsegtr.pth'
model = DefaultPredictor(config)
`

and I am getting KeyError: 'Non-existent config key: MODEL.SOTR'