0

I was wondering if it is possible to run densepose annotations on a mp4 with detectron2?

In the projects folder, you can run densepose with applynet.py but this only works on images. I tried running this commmand

d demo/

python demo.py --config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
  --video-input video.mp4 \
  [--other-options]
  --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

with densepose weights and annotations but Detectron2 gives me this error:

Non-existent config key: MODEL.DENSEPOSE_ON

I know DensePose video exists but it is out of date as it uses caffe2 separated from pytorch.

Is this possible or can you not run on video?

Vidarshan Rathnayake
  • 484
  • 1
  • 10
  • 20
Dark Apostle
  • 189
  • 4
  • 18
  • The line [--other-options] is not to be used literally. This is where you can add other demo.py options if you need them. – mstreffo Jun 08 '22 at 10:00

1 Answers1

0

Easiest approach is to use something like ffmpeg to split your video into frames, and then run detectron2 on each frame.

mstreffo
  • 795
  • 2
  • 8
  • 20