zhszysrh
zhszysrh
I want to test dito with my own classes and images, how can i compute text embedding for my own classes
in SOTS/tree/MOT/CSTrack/lib/core/mot/base_trainer.py,why scale and normalize embedding while training?  after training,just use ps_id to compute cosine distance?
does cstrack supports multi-gpu training?
I need to test metric on my dataset, i follow the instruction ( https://github.com/mlzxy/devit/issues/4) to build CLASS_PROTOTYPES, my dataset has 69 classes. I use the default BG_PROTOTYPES: "weights/initial/background/background_prototypes.vitl14.pth", i get...