Closed shkarupa-alex closed 9 months ago
In both kitti and nyu datasets prompt set as "a photo of" And i don't see any substitution of prompt in training scripts
During training, we do not use any substitution of prompts for the depth estimation task. Only during generation do we utilize the corresponding substitution of prompts.
In both kitti and nyu datasets prompt set as "a photo of" And i don't see any substitution of prompt in training scripts