optimum/amd/ryzenai/models/yolov3/image_processing_yolov3.py [107:135]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if input_data_format == ChannelDimension.FIRST:
                image = image.transpose((2, 0, 1))
                input_data_format = ChannelDimension.LAST

            target_sizes.append(image.shape)

            image = letterbox_image(
                image,
                [self.size["height"], self.size["width"]],
                input_data_format=input_data_format,
            )

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

            image = rescale(
                image=image, scale=self.rescale_factor, data_format=data_format, input_data_format=input_data_format
            )

            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_object_detection(
        self,
        outputs,
        threshold: float = 0.25,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/amd/ryzenai/models/yolov8/image_processing_yolov8.py [117:145]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if input_data_format == ChannelDimension.FIRST:
                image = image.transpose((2, 0, 1))
                input_data_format = ChannelDimension.LAST

            target_sizes.append(image.shape)

            image = letterbox_image(
                image,
                [self.size["height"], self.size["width"]],
                input_data_format=input_data_format,
            )

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

            image = rescale(
                image=image, scale=self.rescale_factor, data_format=data_format, input_data_format=input_data_format
            )

            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_object_detection(
        self,
        outputs,
        threshold: float = 0.25,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -