Documentation on Inference

[1ssb]

Hi, I am very much new to this and just exploring dinov2. Is it kindly possible to release a step by step documentation to run inference for semantic segmentation on a single image or better a video?

[woctezuma]

• Example for how to do inference with this model? #1
• Is this the right way to do inference? #2
• [request] Feature extraction documentation #53

[1ssb]

I prepared a self styled code for Webcam Dinov2, note the change in environment as an image in Linux. https://github.com/1ssb/webcamdino/edit/main/fuser.py