|
|
import os |
|
|
from .clip_encoder import CLIPVisionTower |
|
|
from .imagebind import ImageBindWrapper |
|
|
from .open_clip_encoder import OpenCLIPVisionTower |
|
|
from .hf_vision import HFVisionTower |
|
|
from .siglip_encoder import SigLipVisionTower |
|
|
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 "siglip" in vision_tower: |
|
|
return SigLipVisionTower(vision_tower, vision_tower_cfg=vision_tower_cfg, **kwargs) |
|
|
if use_s2: |
|
|
return CLIPVisionTowerS2(vision_tower, args=vision_tower_cfg, **kwargs) |
|
|
else: |
|
|
return CLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs) |
|
|
elif "siglip" in vision_tower: |
|
|
return SigLipVisionTower(vision_tower, vision_tower_cfg=vision_tower_cfg, **kwargs) |
|
|
elif vision_tower.startswith("hf:"): |
|
|
return HFVisionTower(vision_tower, args=vision_tower_cfg, **kwargs) |
|
|
elif vision_tower in ["imagebind_huge"]: |
|
|
return ImageBindWrapper(vision_tower, args=vision_tower_cfg, **kwargs) |
|
|
elif vision_tower.startswith("open_clip_hub"): |
|
|
return OpenCLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
raise ValueError(f"Unknown vision tower: {vision_tower}") |
|
|
|
|
|
|