optimum/amd/ryzenai/models/hrnet/image_processing_hrnet.py [116:143]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return image

    def preprocess(
        self,
        images: ImageInput,
        return_tensors: Optional[Union[TensorType, str]] = None,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> BatchFeature:
        data_format = data_format if data_format is not None else self.data_format
        self.data_format = data_format

        images = make_list_of_images(images)

        # All transformations expect numpy arrays
        images = [to_numpy_array(image) for image in images]
        # We assume that all images have the same channel dimension format.

        preprocessed_images = []
        target_sizes = []
        for image in images:
            input_data_format = infer_channel_dimension_format(images[0])

            if input_data_format == ChannelDimension.FIRST:
                image = image.transpose((2, 0, 1))
                input_data_format = ChannelDimension.LAST

            target_sizes.append(tuple(image.shape[:2]))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/amd/ryzenai/models/semanticfpn/image_processing_semantic_fpn.py [73:100]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return image

    def preprocess(
        self,
        images: ImageInput,
        return_tensors: Optional[Union[TensorType, str]] = None,
        data_format: Optional[Union[str, ChannelDimension]] = None,
        input_data_format: Optional[Union[str, ChannelDimension]] = None,
    ) -> BatchFeature:
        data_format = data_format if data_format is not None else self.data_format
        self.data_format = data_format

        images = make_list_of_images(images)

        # All transformations expect numpy arrays
        images = [to_numpy_array(image) for image in images]
        # We assume that all images have the same channel dimension format.

        preprocessed_images = []
        target_sizes = []
        for image in images:
            input_data_format = infer_channel_dimension_format(images[0])

            if input_data_format == ChannelDimension.FIRST:
                image = image.transpose((2, 0, 1))
                input_data_format = ChannelDimension.LAST

            target_sizes.append(tuple(image.shape[:2]))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -