def build_vision_tower()

in janus/models/clip_encoder.py [0:0]

• 13 lines of code
• 3 McCabe index (conditional complexity)

    def build_vision_tower(self, vision_tower_params):
        if self.model_name.startswith("siglip"):
            self.select_feature = "same"
            vision_tower = create_siglip_vit(**vision_tower_params)
            forward_kwargs = dict()

        elif self.model_name.startswith("sam"):
            vision_tower = create_sam_vit(**vision_tower_params)
            forward_kwargs = dict()

        else:  # huggingface
            from transformers import CLIPVisionModel

            vision_tower = CLIPVisionModel.from_pretrained(**vision_tower_params)
            forward_kwargs = dict(output_hidden_states=True)

        return vision_tower, forward_kwargs