hkchengrex / MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

Home Page:https://hkchengrex.com/MiVOS/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

-- images mem_profile 2 | RuntimeError: All input tensors must be on the same device. Received cpu and cuda:0

zdhernandez opened this issue · comments

To replicate:

  • create folder with only one image
  • with these settings run: python interactive_gui.py --mem_profile 2 --images ./example/test_folder/
  • select the "click" radio button
  • click on the image to create mask
  • select "scribble" radio button
  • "scribble" an area in the picture
  • runtime error is thrown
    Screenshot from 2021-12-03 22-06-00

Thanks for reporting. It should be fixed now.

@hkchengrex The latest version is not working. This is what I get when I try to run it.
Screenshot from 2021-12-05 11-29-16

hmm it is an unused import. Try again?

@hkchengrex this is what I got now when I tried to run it.
Screenshot from 2021-12-05 12-05-58

This means you have to download the model files as mentioned in the readme