Thanks for your code and novel solution to visual prompt tuning!
If i want to finetune the pretrained model you provided on other works (assumpt that i have standard training pairs), what i understand the manucrafted input-label pairs should be:
stitch training pairs into 2x2 grids, as label.
leave the bottom-right image zero, as input.
Finetune!
Is that right? Could you please tell me how can i do it?
Hello,
Thanks for your code and novel solution to visual prompt tuning!
If i want to finetune the pretrained model you provided on other works (assumpt that i have standard training pairs), what i understand the manucrafted input-label pairs should be:
Is that right? Could you please tell me how can i do it?