remove unused option

models/aggregator.py

@@ -12,14 +12,9 @@ class CLIPVisionCfg:
     width: int = 512
     head_width: int = 64
     mlp_ratio: float = 4.0
-    patch_size: int = 16
-    image_size: Union[Tuple[int, int], int] = 224
 
     ls_init_value: Optional[float] = None  # layer scale initial value
     patch_dropout: float = 0.  # what fraction of patches to dropout during training (0 would mean disabled and no patches dropped) - 0.5 to 0.75 recommended in the paper for optimal results
-    attentional_pool: bool = False  # whether to use attentional pooler in the last embedding layer (overrides pool_type)
-    attn_pooler_queries: int = 256  # n_queries for attentional pooler
-    attn_pooler_heads: int = 8  # n heads for attentional_pooling
     no_ln_pre: bool = False  # disable pre transformer LayerNorm
     pos_embed_type: str = 'none'
     final_ln_after_pool: bool = True  # apply final LayerNorm after pooling
@@ -28,13 +23,6 @@ class CLIPVisionCfg:
     act_kwargs: Optional[dict] = None
     norm_kwargs: Optional[dict] = None
 
-    timm_model_name: Optional[str] = None  # a valid model name overrides layers, width, patch_size
-    timm_model_pretrained: bool = False  # use (imagenet) pretrained weights for named model
-    timm_pool: str = 'avg'  # feature pooling for timm model ('abs_attn', 'rot_attn', 'avg', '')
-    timm_proj: str = 'linear'  # linear projection for timm model output ('linear', 'mlp', '')
-    timm_proj_bias: bool = False  # enable bias final projection
-    timm_drop: float = 0.  # head dropout
-    timm_drop_path: Optional[float] = None  # backbone stochastic depth
     img_embed: bool = False
     cls_embed: bool = False
     projection = False