src/controlnet_aux/segment_anything/build_sam.py [65:86]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ),
            prompt_encoder=PromptEncoder(
            embed_dim=prompt_embed_dim,
            image_embedding_size=(image_embedding_size, image_embedding_size),
            input_image_size=(image_size, image_size),
            mask_in_chans=16,
            ),
            mask_decoder=MaskDecoder(
                    num_multimask_outputs=3,
                    transformer=TwoWayTransformer(
                    depth=2,
                    embedding_dim=prompt_embed_dim,
                    mlp_dim=2048,
                    num_heads=8,
                ),
                transformer_dim=prompt_embed_dim,
                iou_head_depth=3,
                iou_head_hidden_dim=256,
            ),
            pixel_mean=[123.675, 116.28, 103.53],
            pixel_std=[58.395, 57.12, 57.375],
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/controlnet_aux/segment_anything/build_sam.py [130:151]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        ),
        prompt_encoder=PromptEncoder(
            embed_dim=prompt_embed_dim,
            image_embedding_size=(image_embedding_size, image_embedding_size),
            input_image_size=(image_size, image_size),
            mask_in_chans=16,
        ),
        mask_decoder=MaskDecoder(
            num_multimask_outputs=3,
            transformer=TwoWayTransformer(
                depth=2,
                embedding_dim=prompt_embed_dim,
                mlp_dim=2048,
                num_heads=8,
            ),
            transformer_dim=prompt_embed_dim,
            iou_head_depth=3,
            iou_head_hidden_dim=256,
        ),
        pixel_mean=[123.675, 116.28, 103.53],
        pixel_std=[58.395, 57.12, 57.375],
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -