o Zh9A@sdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd l m!Z!e"e#Z$e!d d Gd d d e Z%d gZ&dS)z Image processor class for LeViT.)DictIterableOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging)requires)Zvision)backendsc!seZdZdZdgZddejdddddeef de de e e e fded e d e e e e fd e d ee efd e de eeeefde eeeefddffdd Zejddfdejde e e fdede ee efde ee efdejf ddZedddddddddddejdf dede e de e e e fded e e d e e e e fd e e d e ed e e de eeeefde eeeefde edede ee efdefddZZS)LevitImageProcessora Constructs a LeViT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Wwhether to resize the shortest edge of the input to int(256/224 *`size`). Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`Dict[str, int]`, *optional*, defaults to `{"shortest_edge": 224}`): Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to `(size["height"], size["width"])`. If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to `int(c * (256/224))`. The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to `(size["shortest_egde"] * height / width, size["shortest_egde"])`. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `True`): Whether or not to center crop the input to `(crop_size["height"], crop_size["width"])`. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`Dict`, *optional*, defaults to `{"height": 224, "width": 224}`): Desired image size after `center_crop`. Can be overridden by the `crop_size` parameter in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Controls whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Controls whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`List[int]`, *optional*, defaults to `[0.485, 0.456, 0.406]`): Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`List[int]`, *optional*, defaults to `[0.229, 0.224, 0.225]`): Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method. pixel_valuesTNgp? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stdreturnc  stjdi| |dur|nddi}t|dd}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ | durH| nt |_ | durT| |_dSt |_dS) N shortest_edgeFdefault_to_squareheightwidthr# param_name)super__init__r rr r!r"r#r$r%r&r r'rr() selfrr r!r"r#r$r%r&r'r(kwargs __class__r3_/var/www/auris/lib/python3.10/site-packages/transformers/models/levit/image_processing_levit.pyr5Zs  zLevitImageProcessor.__init__image data_formatinput_data_formatc Kst|dd}d|vr#td|d}t||d|d} | d| dd}d |vs+d |vr4td |t|f|d |d f|||d |S) a- Resize an image. If size is a dict with keys "width" and "height", the image will be resized to `(size["height"], size["width"])`. If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to `int(c * (256/224))`. The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to `(size["shortest_egde"] * height / width, size["shortest_egde"])`. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to (size * height / width, size). resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fr,r*g$I$I?)r r-r=rr.r/r0zFSize dict must have keys 'height' and 'width' or 'shortest_edge'. Got )r r!r<r=)r intr ValueErrorkeysr ) r6r;r r!r<r=r7Z size_dictr*Z output_sizer3r3r:r ys* " zLevitImageProcessor.resizeimagesreturn_tensorsc s|dur|nj}durnj|dur|nj}|dur!|nj}dur*nj| dur3| nj} dur<njdurEnjdurNnjt dddur]nj t ddt |}t |srt dt|| ||d dd |D}|rt|d rtd durt|d |rfd d |D}|rfd d |D}|rƇfdd |D}| rԇfdd |D}fdd |D}d|i}t|| dS)a Preprocess an image or batch of images to be used as input to a LeViT model. Args: images (`ImageInput`): Image or batch of images to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`Dict[str, int]`, *optional*, defaults to `self.size`): Size of the output image after resizing. If size is a dict with keys "width" and "height", the image will be resized to (height, width). If size is a dict with key "shortest_edge", the shortest edge value `c` is rescaled to int(`c` * (256/224)). The smaller edge of the image will be matched to this value i.e, if height > width, then image will be rescaled to (size * height / width, size). resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resiizing the image. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether to center crop the image. crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the output image after center cropping. Crops images to (crop_size["height"], crop_size["width"]). do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image pixel values by `rescaling_factor` - typical to values between 0 and 1. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Factor to rescale the image pixel values by. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image pixel values by `image_mean` and `image_std`. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Mean to normalize the image pixel values by. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Standard deviation to normalize the image pixel values by. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`str` or `ChannelDimension`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. NFr,r#r1zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) r$r%r&r'r(r"r#rr r!cSsg|]}t|qSr3)r.0r;r3r3r: sz2LevitImageProcessor.preprocess..rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.csg|] }j|dqS)r=)r rD)r=r!r6r r3r:rF"scsg|] }j|dqSrG)Z center_croprD)r#r=r6r3r:rF%csg|] }j|dqSrG)ZrescalerD)r=r%r6r3r:rF(rHcsg|] }j|dqSrG) normalizerD)r'r(r=r6r3r:rF+scsg|] }t|dqS))Zinput_channel_dim)r rD)r<r=r3r:rF/sr)dataZ tensor_type)rr!r"r$r%r&r'r(r r r#rrr@rrloggerZ warning_oncerr)r6rBrr r!r"r#r$r%r&r'r(rCr<r=rJr3) r#r<r'r(r=r!r%r6r r: preprocesssfD      zLevitImageProcessor.preprocess)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBICUBICr rboolrrstrr?rfloatrr5npZndarrayrr rZFIRSTrrrrL __classcell__r3r3r8r:r/s'     #  7     r)'rPtypingrrrrnumpyrTZimage_processing_utilsrrr Zimage_transformsr r r Z image_utilsr rrrrrrrrrrutilsrrrZutils.import_utilsrZ get_loggerrMrKr__all__r3r3r3r:s4