Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

what is s2 in vision load tower and how it effects training #20

Open
Jayantverma2 opened this issue May 8, 2024 · 1 comment
Open

Comments

@Jayantverma2
Copy link

import os
from .clip_encoder import CLIPVisionTower, CLIPVisionTowerS2

def build_vision_tower(vision_tower_cfg, **kwargs):
vision_tower = getattr(vision_tower_cfg, 'mm_vision_tower', getattr(vision_tower_cfg, 'vision_tower', None))
is_absolute_path_exists = os.path.exists(vision_tower)
use_s2 = getattr(vision_tower_cfg, 's2', False)
if is_absolute_path_exists or vision_tower.startswith("openai") or vision_tower.startswith("laion") or "ShareGPT4V" in vision_tower:
if use_s2:
return CLIPVisionTowerS2(vision_tower, args=vision_tower_cfg, **kwargs)
else:
return CLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs)

raise ValueError(f'Unknown vision tower: {vision_tower}')
@mmaaz60
Copy link
Member

mmaaz60 commented May 10, 2024

Hi @Jayantverma2,

Thank you for your interest in our work. In order to use S2, you have to use the lates LLaVA code base. Its implemented here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants