optimum/amd/ryzenai/models/hrnet/image_processing_hrnet.py [161:184]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            image = rescale(
                image=image, scale=self.rescale_factor, data_format=data_format, input_data_format=input_data_format
            )

            image = self.normalize(
                image,
                mean=self.image_mean,
                std=self.image_std,
                data_format=data_format,
                input_data_format=input_data_format,
            )

            image = np.ascontiguousarray(image, dtype=np.float32)

            preprocessed_images.append(image)

        data = {"pixel_values": preprocessed_images, "target_sizes": target_sizes}
        encoded_inputs = BatchFeature(data=data, tensor_type=return_tensors)

        return encoded_inputs

    def post_process_semantic_segmentation(
        self,
        outputs,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/amd/ryzenai/models/semanticfpn/image_processing_semantic_fpn.py [104:127]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            image = rescale(
                image=image, scale=self.rescale_factor, data_format=data_format, input_data_format=input_data_format
            )

            image = self.normalize(
                image,
                mean=self.image_mean,
                std=self.image_std,
                data_format=data_format,
                input_data_format=input_data_format,
            )

            image = np.ascontiguousarray(image, dtype=np.float32)

            preprocessed_images.append(image)

        data = {"pixel_values": preprocessed_images, "target_sizes": target_sizes}
        encoded_inputs = BatchFeature(data=data, tensor_type=return_tensors)

        return encoded_inputs

    def post_process_semantic_segmentation(
        self,
        outputs,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -