optimum/amd/ryzenai/models/yolov5/image_processing_yolov5.py [139:156]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        target_sizes: Union[TensorType, List[Tuple]] = None,
        agnostic_nms=False,
        merge_nms=False,
        max_detections=1000,
        data_format: Union[str, ChannelDimension] = None,
    ):
        data_format = data_format if data_format is not None else self.data_format

        if merge_nms:
            raise ValueError("Merge NMS is not yet supported!")

        outputs = list(outputs.values())

        if not isinstance(outputs[0], torch.Tensor):
            outputs = [torch.tensor(out) for out in outputs]

        if data_format == ChannelDimension.LAST:
            outputs = [torch.permute(out, (0, 3, 1, 2)) for out in outputs]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/amd/ryzenai/models/yolov8/image_processing_yolov8.py [147:164]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        target_sizes: Union[TensorType, List[Tuple]] = None,
        agnostic_nms=False,
        merge_nms=False,
        max_detections=1000,
        data_format: Union[str, ChannelDimension] = None,
    ):
        data_format = data_format if data_format is not None else self.data_format

        if merge_nms:
            raise ValueError("Merge NMS is not yet supported!")

        outputs = list(outputs.values())

        if not isinstance(outputs[0], torch.Tensor):
            outputs = [torch.tensor(out) for out in outputs]

        if data_format == ChannelDimension.LAST:
            outputs = [torch.permute(out, (0, 3, 1, 2)) for out in outputs]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -