o ZhH@sdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZm Z erSddl!Z!e "e#Z$Gd d d e Z%d gZ&dS) z'Image processor class for EfficientNet.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)rescaleresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc#s4eZdZdZdgZddejjdddddddddf dede e e e fd e d ed e e e e fd ee efd ededede eeeefde eeeefdeddffdd Ze jddfdejde e e fd e de ee efde ee efdejf ddZ   d#dejdee efdede ee efde ee eff ddZedddddddddddddejdfdede ede e e e fd e ed e e e e fde ed e ed e ede ede eeeefde eeeefde ed e ee efdede ee efdejjf d!d"ZZS)$EfficientNetImageProcessoraN Constructs a EfficientNet image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by `do_resize` in `preprocess`. size (`Dict[str, int]` *optional*, defaults to `{"height": 346, "width": 346}`): Size of the image after `resize`. Can be overridden by `size` in `preprocess`. resample (`PILImageResampling` filter, *optional*, defaults to 0): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_center_crop (`bool`, *optional*, defaults to `False`): Whether to center crop the image. If the input size is smaller than `crop_size` along any edge, the image is padded with 0's and then center cropped. Can be overridden by `do_center_crop` in `preprocess`. crop_size (`Dict[str, int]`, *optional*, defaults to `{"height": 289, "width": 289}`): Desired output size when applying center-cropping. Can be overridden by `crop_size` in `preprocess`. 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. rescale_offset (`bool`, *optional*, defaults to `False`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`): 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 (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`): 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. include_top (`bool`, *optional*, defaults to `True`): Whether to rescale the image again. Should be set to True if the inputs are used for image classification. pixel_valuesTNFgp? do_resizesizeresampledo_center_crop crop_sizerescale_factorrescale_offset do_rescale do_normalize image_mean image_std include_topreturnc  stjdi| |dur|nddd}t|}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ | |_ | durJ| nt |_ | durS| nt|_| |_dS)NiZ)heightwidthi!r" param_name)super__init__r rrr r!r"r%r#r$r&r r'rr(r))selfrrr r!r"r#r$r%r&r'r(r)kwargs __class__r/m/var/www/auris/lib/python3.10/site-packages/transformers/models/efficientnet/image_processing_efficientnet.pyr1Ws"  z#EfficientNetImageProcessor.__init__image data_formatinput_data_formatcKsTt|}d|vs d|vrtd||d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.NEAREST`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.NEAREST`. data_format (`ChannelDimension` or `str`, *optional*): 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. - `"none"` or `ChannelDimension.NONE`: image in (height, width) 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. Returns: `np.ndarray`: The resized image. r+r,zFThe `size` dictionary must contain the keys `height` and `width`. Got )rr r8r9)r ValueErrorkeysr )r2r7rr r8r9r3Z output_sizer/r/r6r {s#z!EfficientNetImageProcessor.resizescaleoffsetcKs(t|f|||d|}|r|d}|S)a Rescale an image by a scale factor. If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is 1/127.5, the image is rescaled between [-1, 1]. image = image * scale - 1 If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1]. image = image * scale Args: image (`np.ndarray`): Image to rescale. scale (`int` or `float`): Scale to apply to the image. offset (`bool`, *optional*): Whether to scale the image in both negative and positive directions. 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. )r<r8r9r )r2r7r<r=r8r9r3Zrescaled_imager/r/r6r sz"EfficientNetImageProcessor.rescaleimagesreturn_tensorsc s |dur|nj}durnj|dur|nj}|dur!|nj}dur*njdur3nj| dur<| nj} durEnjdurNnj| durW| nj } dur` nj t  durmnj t ddt |}t|stdt|| || d dd|D}|rt|drtd durt|d|r fd d|D}|rɇfd d|D}|rׇfd d|D}| rfd d|D}| rfdd|D}fdd|D}d|i}t||dS)a Preprocess an image or batch of images. Args: images (`ImageInput`): Image 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 image after `resize`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): PILImageResampling filter to use if resizing the image Only has an effect if `do_resize` is set to `True`. 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 image after center crop. If one edge the image is smaller than `crop_size`, it will be padded with zeros and then cropped do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. rescale_offset (`bool`, *optional*, defaults to `self.rescale_offset`): Whether to rescale the image between [-scale_range, scale_range] instead of [0, scale_range]. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Image mean. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. include_top (`bool`, *optional*, defaults to `self.include_top`): Rescales the image again for image classification if set to True. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - `None`: 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 (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. Can be one of: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `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. Nr"r-zkInvalid 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"rrr cSsg|]}t|qSr/)r.0r7r/r/r6 >sz9EfficientNetImageProcessor.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))r7rr r9)r rB)r9r r2rr/r6rDKcsg|] }j|dqS))r7rr9)Z center_croprB)r"r9r2r/r6rDQscsg|] }j|dqS))r7r<r=r9r?rB)r9r#r$r2r/r6rDVs csg|] }j|dqS)r7meanZstdr9 normalizerB)r'r(r9r2r/r6rD^rEcsg|] }j|ddqS)rrFrHrB)r(r9r2r/r6rDdrEcsg|] }t|dqS))Zinput_channel_dim)r rB)r8r9r/r6rDisr)dataZ tensor_type)rr r!r%r#r$r&r'r(r)rr r"rrr:rrloggerZ warning_oncerr)r2r@rrr r!r"r%r#r$r&r'r(r)rAr8r9rJr/) r"r8r'r(r9r r#r$r2rr6 preprocesss~G     z%EfficientNetImageProcessor.preprocess)TNN)__name__ __module__ __qualname____doc__Zmodel_input_namesPILZImageZNEARESTboolrrstrintrrfloatrr1npZndarrayrr r rZFIRSTrrrL __classcell__r/r/r4r6r.s&      (  4  (     r)'rPtypingrrrrnumpyrVZimage_processing_utilsrrr Zimage_transformsr r r Z image_utilsr rrrrrrrrrrutilsrrrrrQZ get_loggerrMrKr__all__r/r/r/r6s4   E