Is there anyway that I can use your weight to do inference via webcam? Would it be prossible if you could provide inference part.
I have tried to use the demo code from detectron2 https://github.com/facebookresearch/detectron2/tree/main/demo.
I copied whole demo folder into AirDet folder;
Then I changed the config file from "configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml" to "./configs/fsod/R101/test_R_101_C4_1x_coco3.yaml", which is from your config folder.
But, I got
KeyError: 'Non-existent config key: DATASETS.TESTSHOTS'
when code runs self.merge_from_other_cfg(loaded_cfg)
You may need to re-write the config.py file in our fewx code, and import config from fewx instead of detectron2.
Generally, the inference is in 2 steps:
generate support features from support images.
Inference on Query images.
I believe it is possible to integrate any detectron2 functions into our library.
Is there anyway that I can use your weight to do inference via webcam? Would it be prossible if you could provide inference part. I have tried to use the demo code from detectron2 https://github.com/facebookresearch/detectron2/tree/main/demo. I copied whole demo folder into AirDet folder; Then I changed the config file from "configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml" to "./configs/fsod/R101/test_R_101_C4_1x_coco3.yaml", which is from your config folder. But, I got
KeyError: 'Non-existent config key: DATASETS.TESTSHOTS' when code runs
self.merge_from_other_cfg(loaded_cfg)