o Zh /@sdZddlmZmZmZmZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZee Z!erTddl"Z"Gd d d eZ#d gZ$dS) z!Image processor class for SigLIP.)DictListOptionalUnion)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingNcsbeZdZdZdgZddejddddddf dedee e e fded ed e e e fd ed ee e ee fd ee e ee fdeeddffdd Zedddddddddejddf dedeedee e e fded eed ee d eed ee e ee fd ee e ee fdee e efdeedee e efdeedejjfddZZS)SiglipImageProcessora Constructs a SigLIP 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 the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after resizing. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Can be overridden 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 overridden 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 overridden by `rescale_factor` in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image by the specified mean and standard deviation. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `[0.5, 0.5, 0.5]`): 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 `[0.5, 0.5, 0.5]`): 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  stjdi| |dur|nddd}|dur|nt}|dur"|nt}||_||_||_||_||_||_ ||_ ||_ | |_ dS)N)heightwidth) super__init__r rrrr r!r"r#r$r%r&) selfrrr r!r"r#r$r%r&kwargs __class__r+a/var/www/auris/lib/python3.10/site-packages/transformers/models/siglip/image_processing_siglip.pyr-Rs  zSiglipImageProcessor.__init__imagesreturn_tensors data_formatinput_data_formatc s|dur|nj}|dur|nj}t|ddd}durnj|dur(|nj}dur1nj|dur:|nj}durCnjdurLnj| durU| nj } t |}t |sdt dt ||||d| rydd|D}d d|D}|rt|d rtd durt|d |r|d |d fdd|D}|rfdd|D}|rɇfdd|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 resizing. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. 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. 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 use for normalization. Only has an effect if `do_normalize` is set to `True`. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. 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. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. NrF) param_nameZdefault_to_squarezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r!r"r#r$r%rrr cSg|]}t|qSr+)r .0imager+r+r2 z3SiglipImageProcessor.preprocess..cSr8r+)rr9r+r+r2r<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.r)r*cs g|] }t|fdqS))r;rr r6)r r9)r)r6r r*r+r2r<scsg|] }j|dqS))r;scaler6)Zrescaler9)r6r"r.r+r2r<scsg|] }j|dqS))r;meanZstdr6) normalizer9)r$r%r6r.r+r2r<scsg|] }t|dqS))Zinput_channel_dim)r r9)r5r6r+r2r<sr)dataZ tensor_type)rrr r r!r"r#r$r%r&rr ValueErrorrrloggerZ warning_oncerr)r.r3rrr r!r"r#r$r%r4r5r6r&rAr+) r5r)r$r%r6r r"r.r*r2 preprocessnsh?    zSiglipImageProcessor.preprocess)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBICUBICboolrrstrintrfloatrr-rrZFIRSTrrPILZImagerD __classcell__r+r+r0r2r0s         r)%rHtypingrrrrZimage_processing_utilsrrr Zimage_transformsr r r Z image_utilsr rrrrrrrrrrutilsrrrrZ get_loggerrErCrMr__all__r+r+r+r2s4  E