about train my class segmentation

[xiongzhu666]

hi，thanks for your great working，I want to train my single class segmentation based on your project，I have some doubt about training：

1. the dataset format：the data directory should include image and mask，the mask is binary single channel image，right？？
2. could I run train.py directly？？what else should I consider and modify？？ thanks best regard

[xuebinqin]

1. image with RGB channels [0,255], Mask with one channel (0-background, 255-foreground).
2. yes, you can train with 'train.py' directly. just modify the training data path should work. If you want, you can add the validation process in the training code.

On Mon, Jun 7, 2021 at 6:34 AM xiongzhu666 @.***> wrote:

hi，thanks for your great working，I want to train my single class segmentation based on your project，I have some doubt about training：

1. the dataset format：the data directory should include image and mask，the mask is binary single channel image，right？？
2. could I run train.py directly？？what else should I consider and modify？？ thanks best regard

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/dennisbappert/u-2-net-portrait/issues/8, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORPD2PILRETGWXD4E43TRQV4PANCNFSM46GV5KTQ .

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/

[Testhjf]

@xuebinqin @dennisbappert hello sir，when i train ，it propers bellow problems： hydra.errors.InstantiationException: Top level config has to be OmegaConf DictConfig, plain dict, or a Structured Config class or instance。 how can i deal with it ？ thanks