mmtracking
mmtracking copied to clipboard
how to generate mask but video?
seems mmtracking only generate videos, so how to generate the mask png images? like https://github.com/foolwood/SiamMask.
We support VIS tasks that can predict masks. Now, the SOT methods we support can not predict masks.
Can you please provide details on how to infer a video for the VIS task and output the instance_id segmented masks?