Open gaurav-g-12 opened 3 months ago
Do we need to provide mask for pre-training ViT base
Sorry for the late reply. Can you describe it more specifically?
Are there any scripts for pertaining the model?
Do we need to provide mask for pre-training ViT base
yes! You can generate pseudo labels by CCD [https://github.com/TongkunGuan/CCD/tree/main/mask_create].
Do we need to provide mask for pre-training ViT base