qiD:dZddlZddlmZmZmZddlmZm Z m Z ddl m Z m Z mZmZmZmZmZmZmZmZmZddlmZmZmZmZerddlZej:eZGdd eZ d gZ!y) zImage processor class for BLIP.N)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingcTeZdZdZdgZddej ddddddf dedee e fdzded ed e e zd ed e e e zdzd e e e zdzdeddffd Z ej ddfdejdee e fdede ezdzde ezdzdejf dZeddddddddddej&df dededzdee e fdzdedzd edzd e dzd edzd e e e zdzd e e e zdzde ezdzdedzdede ezdzdej.j.fdZxZS)BlipImageProcessora Constructs a BLIP 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 the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `{"height": 384, "width": 384}`): Size of the output image after resizing. 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. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` 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. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` 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. 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. 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. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  t |di| ||nddd}t|d}||_||_||_||_||_||_||nt|_ ||nt|_ | |_ y)Ni)heightwidthTdefault_to_square)super__init__rrrrrr r!r r"r r#r$) selfrrrrr r!r"r#r$kwargs __class__s `/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/blip/image_processing_blip.pyr-zBlipImageProcessor.__init__Ps "6"'tc-JTT:"   $,((2(>*DT&/&;,image data_formatinput_data_formatc t|}d|vsd|vrtd|j|d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. r'r(zFThe `size` dictionary must contain the keys `height` and `width`. Got )rrr4r5)r ValueErrorkeysr)r.r3rrr4r5r/ output_sizes r1rzBlipImageProcessor.resizelsyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r2imagesreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} ||n |j}t|d}|j|}t|}t|s tdt||||| |||| r|Dcgc] }t|}}|Dcgc] }t!|}}|r#t#|drt$j'd| t)|d} |r"|Dcgc]}|j+|||| }}|r!|Dcgc]}|j-||| }}|r"|Dcgc]}|j/||| | }}|Dcgc]}t1|| | }}t3d |i| }|Scc}wcc}wcc}wcc}wcc}wcc}w) 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`): Controls the size of the image after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. 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 to normalize the image by if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to normalize the image by if `do_normalize` is set to `True`. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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)zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)rr r!r"r#rrrrzIt 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.)r3rrr5)r3scaler5)r3meanstdr5)input_channel_dimr)data tensor_type)rrrr r!r"r#r$rr fetch_imagesrrr7rrrrlogger warning_oncerrrescale normalizer r)r.r:rrrrr r!r"r#r;r$r4r5r3encoded_outputss r1 preprocesszBlipImageProcessor.preprocesssf|"+!6IDNN '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^'tTYYTU;""6*)&1F#rs s%!)%!  9?@nU+@F@6<vay I  $ %dXYj kF $ 5Rc dF $U^opF ou ej '{N_ `  '^V,DR`aOA=    s$)G!G&G+4G0G59G:)__name__ __module__ __qualname____doc__model_input_namesrBICUBICbooldictstrintfloatlistr-npndarrayr rrFIRSTr rPILImagerI __classcell__)r0s@r1rr+s D((&*'9'A'A&-!1504#--38nt#-% -  - e --DK'$.-4;&--- -@(:'A'A59;? . zz. 38n. % . ++d2 . !11D8 .  . `%&"&&*.2"&'+$(150426&*(8(>(>;?AA$;A38nt# A %t+ A 4K A ATkADK'$.A4;&-Aj(4/At A&A!11D8A A'Ar2r)"rMnumpyrVimage_processing_utilsrrrimage_transformsrrr image_utilsr r r r rrrrrrrutilsrrrrrY get_loggerrJrDr__all__r+r2r1rcso&UUSS    _^   H %s+sl r2