def _get_maskmem_pos_enc()

in sam2/sam2_video_predictor.py [0:0]

• 17 lines of code
• 7 McCabe index (conditional complexity)

    def _get_maskmem_pos_enc(self, inference_state, current_out):
        """
        `maskmem_pos_enc` is the same across frames and objects, so we cache it as
        a constant in the inference session to reduce session storage size.
        """
        model_constants = inference_state["constants"]
        # "out_maskmem_pos_enc" should be either a list of tensors or None
        out_maskmem_pos_enc = current_out["maskmem_pos_enc"]
        if out_maskmem_pos_enc is not None:
            if "maskmem_pos_enc" not in model_constants:
                assert isinstance(out_maskmem_pos_enc, list)
                # only take the slice for one object, since it's same across objects
                maskmem_pos_enc = [x[0:1].clone() for x in out_maskmem_pos_enc]
                model_constants["maskmem_pos_enc"] = maskmem_pos_enc
            else:
                maskmem_pos_enc = model_constants["maskmem_pos_enc"]
            # expand the cached maskmem_pos_enc to the actual batch size
            batch_size = out_maskmem_pos_enc[0].size(0)
            expanded_maskmem_pos_enc = [
                x.expand(batch_size, -1, -1, -1) for x in maskmem_pos_enc
            ]
        else:
            expanded_maskmem_pos_enc = None
        return expanded_maskmem_pos_enc