sam-hq
sam-hq copied to clipboard
Can the train.py ssupport the training for Light HQ-SAM?
Hi,
Currently in the train.py, only model_type in ["vit_b","vit_l", "vit_h"] are supported. My question is, can I use the train.py to train the Light HQ-SAM (model_type = "vit_tiny")? If yes, how can I modify train.py to support the light version?
Thanks.
Hello, I have the same problem, have you solved it yet?