File size: 593 Bytes
1fea0a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 |
from .clip_encoder import CLIPVisionTower
from .eva_encoder import EVAVisionTower
def build_vision_tower(vision_tower_cfg, **kwargs):
vision_tower = getattr(vision_tower_cfg, 'mm_vision_tower', getattr(vision_tower_cfg, 'vision_tower', None))
if vision_tower.startswith("openai") or vision_tower.startswith("laion"):
return CLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs)
elif vision_tower.startswith("eva_vit_g"):
return EVAVisionTower(vision_tower, args=vision_tower_cfg, **kwargs)
raise ValueError(f'Unknown vision tower: {vision_tower}')
|