detector freeze problem

[YOOHYOJEONG]

Hi.

I'm going to freeze the parameters of detector as you say(#126).

In qdtrack/models/mot/qdtrack.py, I tried to freeze the detector using freeze_detector(freeze_detector = True).
But, when freeze_detector = True, self.detector, I got this error.

Traceback (most recent call last):
File "tools/train.py", line 169, in
main()
File "tools/train.py", line 140, in main
test_cfg=cfg.get('test_cfg'))
File "/workspace/qdtrack/qdtrack/models/builder.py", line 15, in build_model
return build(cfg, MODELS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
File "/workspace/mmcv/mmcv/cnn/builder.py", line 27, in build_model_from_cfg
return build_from_cfg(cfg, registry, default_args)
File "/workspace/mmcv/mmcv/utils/registry.py", line 72, in build_from_cfg
raise type(e)(f'{obj_cls.name}: {e}')
AttributeError: QDTrack: 'QDTrack' object has no attribute 'backbone'

Here is the config file I used.

I think,

be caused by self.detector.

How can I put the backbone and neck, rpn_head, roi_head.bbox_head of the detector config file(/configs/base/faster_rcnn_r50_fpn.py) in self.detector?

Thank you.

[YOOHYOJEONG]

Hi, I solved this problem. But I got a new question afterwards.

I want to inference using detector I trained using MMCV and tracker obtained when I training only trackers by freezing the detector together.

I want to use tools/inference.py. I think checkpoint argument in inference.py means I get when I training at once without freezing anything( joint training).

How can I use each checkpoint of the detector and tracker in tools/inference.py?

Thank you.