facebookresearch / facebookresearch/detectron2
inference on a frame sequence
Open
densepose
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
Hey there,
I was trying to inference on a sequence of images with DensePose with the following code:
!python ./apply_net.py show configs/densepose_rcnn_R_50_FPN_s1x.yaml https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl "frame*.jpg" dp_contour,bbox --output output_frame.png
but it seems that DensePose is not converting the right sequence of images so I would get a shuffled video which is useless. Any idea how to use this command to get the right output_frame sequence?
Thanks
Contributor guide
Assessment
This issue has not been assessed yet.