Detectron2: No Detection Output seen after running

[deeplearner93]

I run the following line of code in the terminal:
python3 demo.py --config-file ../configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml --input image.jpg

I get the input image without any detections or bounding box.

[ppwwyyxx]

Please follow the command in instructions https://github.com/facebookresearch/detectron2/blob/master/GETTING_STARTED.md#inference-demo-with-pre-trained-models

[deeplearner93]

@ppwwyyxx I think that is exactly my question. The instructions followed is not giving the desired output. I would need support on something more other than the instructions which is a little unclear. And I really respect the way you are answering the queries. Thank you.

[ppwwyyxx]

The instruction requires picking and using a model file:

Pick a model and its config file from model zoo, for example, mask_rcnn_R_50_FPN_3x.yaml.
We provide demo.py that is able to run builtin standard models. Run it with:
cd demo/
python demo.py --config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
--input input1.jpg input2.jpg \
[--other-options]
--opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl
The configs are made for training, therefore we need to specify MODEL.WEIGHTS to a model from model zoo for evaluation.

[qustions]

@deeplearner93 did you solve that issue because I am also not getting the prediction on the output image