the video is shown with a white screen.

[hhy150]

In the Infer stage, follow the readme instruction（Running PDVC on Your Own Videos）, but for different videos, always generate captions with the same sentence: "The video is shown with a white screen."

[ziishuo]

Hi, I don't know if you solved the problem. I'll tell you about my solution: Compile the deformable attention layer correctly. In addition, I used a 3070ti laptop GPU for inference, and then I switched to a 3090ti GPU, which has more video memory.
The compilation result is as follows:
Installed /root/Project/anaconda3/envs/PDVC/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg
Processing dependencies for MultiScaleDeformableAttention==1.0
Finished processing dependencies for MultiScaleDeformableAttention==1.0