A simple demo with CO-DETR throws the following error.
The model and loaded state dict do not match exactly
unexpected key in source state_dict: query_head.label_embedding.weight
missing keys in source state_dict: query_head.dn_generator.label_embedding.weight
/longdata/anurag_storage/2PCNet/LLIE/mmdetection/mmdet/apis/det_inferencer.py:130: UserWarning: dataset_meta or class names are not saved in the checkpoint's meta data, use COCO classes by default.
warnings.warn(
02/19 14:29:41 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "function" registry tree. As a workaround, the current "function" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized.
/home/aghosh/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/visualization/visualizer.py:196: UserWarning: Failed to add <class 'mmengine.visualization.vis_backend.LocalVisBackend'>, please provide the `save_dir` argument.
warnings.warn(f'Failed to add {vis_backend.__class__}, '
Traceback (most recent call last):
File "demo/image_demo.py", line 192, in <module>
main()
File "demo/image_demo.py", line 182, in main
inferencer.model.test_cfg.chunked_size = chunked_size
AttributeError: 'list' object has no attribute 'chunked_size'
Checklist
Describe the bug
A simple demo with CO-DETR throws the following error.
Reproduction