search

xuebinqin / DIS

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
Apache License 2.0
2.11k stars 244 forks source link

Regarding whether pre-trained encoders are necessary #92

Open babyta opened 8 months ago

babyta commented 8 months ago

First of all, thank you very much for your work. When ’interm_sup’ is set to True, the encoder will be trained. My data set has tens of thousands of images. I would like to ask if it is necessary to train the encoder at this time.

Kaustubh-cpu commented 4 days ago

hello @babyta

Do you got any idea about gt_encoder

Kaustubh-cpu commented 4 days ago

When i am setting hypar["interm_sup"] = True

it is giving me the error gos_dataloader = train_dataloaders[0] NameError: name 'train_dataloaders' is not defined