sam-hq
sam-hq copied to clipboard
Train Light HQ-SAM
Hello, how can I get the pretrained_checkpoint of Light hqsam during training?
Hi, did you find a solution now?
parser.add_argument("--model-type", type=str, default="vit_l", help="The type of model to load, in ['vit_h', 'vit_l', 'vit_b']") has no option for a light HQ based on ViT-tiny.
So how to get the Light HQ SAM model on custom datasets training?