sg=dZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z m!Z!e rddl"Z"e!jFe$Z%Gd d e Z&y) z#Image processor class for ConvNeXT.)DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict) center_cropget_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingcLeZdZdZdgZdddej dddddf dedee e fde d ed ed e e e fd ed e e e ee fde e e ee fddffd Zej ddfdej$dee e fde d ede e e efde e e efdej$fdZeddddddddddej,df dededee e fde d ed ed e d ed e e e ee fde e e ee fde e e efdede e e efdej4j4fdZxZS)ConvNextImageProcessora5 Constructs a ConvNeXT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Controls whether to resize the image's (height, width) dimensions to the specified `size`. Can be overriden by `do_resize` in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 384}`): Resolution of the output image after `resize` is applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. Can be overriden by `size` in the `preprocess` method. crop_pct (`float` *optional*, defaults to 224 / 256): Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size < 384. Can be overriden by `crop_pct` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overriden by `resample` in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overriden by `do_rescale` in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overriden by `rescale_factor` 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. pixel_valuesTNgp? do_resizesizecrop_pctresample do_rescalerescale_factor do_normalize image_mean image_stdreturnc  t |di| ||nddi}t|d}||_||_||nd|_||_||_||_||_ ||nt|_ | | |_ yt|_ y)N shortest_edgeFdefault_to_squareg?)super__init__r r!r"r#r$r%r&r'rr(rr)) selfr!r"r#r$r%r&r'r(r)kwargs __class__s i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/convnext/image_processing_convnext.pyr2zConvNextImageProcessor.__init__Ys "6"'tos-CTU;" $,$8i   $,((2(>*DZ&/&;AVimage data_formatinput_data_formatc t|d}d|vrtd|j|d}|dkr@t||z } t || d|} t d || |||d|}t d |||f||d|St |f||f|||d |S) a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Dictionary of the form `{"shortest_edge": int}`, specifying the size of the output image. If `size["shortest_edge"]` >= 384 image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"] / crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. crop_pct (`float`): Percentage of the image to crop. Only has an effect if size < 384. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred from the input image. Fr.r,z6Size dictionary must contain 'shortest_edge' key. Got r-)r"r/r:)r8r"r$r9r:)r8r"r9r:)r"r$r9r:r0)r ValueErrorkeysintr r r ) r3r8r"r#r$r9r:r4r,resize_shortest_edge resize_sizes r6r zConvNextImageProcessor.resizeus>TU; $ &UVZV_V_VaUbcd d_- 3 #&}x'?#@ 60E]nK !'"3   E#]3'"3    #]3!'"3    r7imagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} ||n |j}t|d}t|}t|s tdt|||| | ||||Dcgc] }t|}}t|dr|rt j#d| t%|d} |r#|Dcgc]}|j'||||| }}|r!|Dcgc]}|j)||| }}|r"|Dcgc]}|j+|| | | }}|Dcgc]}t-|| | }}d |i}t/|| Scc}wcc}wcc}wcc}wcc}w) aW 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 output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. crop_pct (`float`, *optional*, defaults to `self.crop_pct`): Percentage of the image to crop if size < 384. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of `PILImageResampling`, filters. Only has an effect if `do_resize` is set to `True`. 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`. 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. 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 (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output 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. - Unset: Use the channel dimension format of the input image. 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. Fr.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"r$rzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r8r"r#r$r:)r8scaler:)r8meanstdr:)input_channel_dimr )data tensor_type)r!r#r$r%r&r'r(r)r"r rrr<rrrlogger warning_oncerr rescale normalizerr )r3rAr!r"r#r$r%r&r'r(r)rBr9r:r8rHs r6 preprocessz!ConvNextImageProcessor.preprocesssBB"+!6IDNN '38'38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN 'tTYYTU;$V,F#:  &!)%! 6<vay I   $  dXduF $ 5Rc dF $U^opF ou ej '{N_ `  '>BBK=   sF7%F< G-GG )__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrstrr>floatrrrr2BICUBICnpndarrayrr rFIRSTrrPILImagerN __classcell__)r5s@r6rr3s!F((#'9'B'B,3!:>9=WW38nW W % W  Wc5j)WWU5$u+#567WE%e"456W WB(:'A'A>BDHCzzC38nC C % C eC)9$9:; C$E#/?*?$@AC CJ%&#'+ $!:>9=;?(8(>(>DHECECEC38n EC  EC % ECECECECU5$u+#567ECE%e"456EC!sJ!78EC&EC$E#/?*?$@AEC EC'ECr7r)'rRtypingrrrrnumpyrYimage_processing_utilsrr r image_transformsr r r r image_utilsrrrrrrrrrrrutilsrrrrr\ get_loggerrOrJrr0r7r6rfsp*..UU    _^   H %MC/MCr7