sam-hq
sam-hq copied to clipboard
Regarding multi class training
Hello author, first of all, thank you very much for your outstanding contribution. I am currently working on HumanParsing, which involves segmenting multiple parts of the human body such as hair, clothing, skin, etc. If my data consists of original images and grayscale images with label values ranging from 0 to 18, can I use Sam HQ for training?
Can SAM-HQ support multiple instance segmentation in the same image ?
The code and the dataset contain only one mask per image.