Fix of the demo.py script for running panoptic segmentation on video in the Detectron2 Tutorial.ipynb

[Reka-Berci-Hajnovics]

In the Detectron2 Tutorial.ipynb Google Colab notebook the segmentation on a video section is broken: Detectron2 Tutorial.ipynb

See the issue with a solution: #5368

The problem is the relative paths used in the demo.py script. The demo.py script has been updated in this pull request to remove this issue.

Code block from the Detectron2 Tutorial.ipynb notebook:

# Run frame-by-frame inference demo on this video (takes 3-4 minutes) with the "demo.py" tool we provided in the repo.
#!git clone https://github.com/facebookresearch/detectron2
# Note: this is currently BROKEN due to missing codec. See https://github.com/facebookresearch/detectron2/issues/2901 for workaround.
#%run detectron2/demo/demo.py --config-file detectron2/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml --video-input video-clip.mp4 --confidence-threshold 0.6 --output video-output.mkv \
#  --opts MODEL.WEIGHTS detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/model_final_cafdb1.pkl

#Fix:
#Set the path to the parent 'detectron2' folder
sys.path.insert(0, os.path.abspath('detectron2'))
#Open the detectron2 folder in the left side panel of Google Colab. In the demo folder you can find the demo.py script.
#Now you can modify the demo.py script. Comment or delete the import of VisualizationDemo, and add the following import:
#from predictor import VisualizationDemo
#When the pull request will be accepted, the manual modification of demo.py script will no longer be needed.

%run detectron2/demo/demo.py --config-file detectron2/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml --video-input video-clip.mp4 --confidence-threshold 0.6 --output video-output.mkv \
  --opts MODEL.WEIGHTS detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/model_final_cafdb1.pkl

[facebook-github-bot]

Hi @Reka-Berci-Hajnovics!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!