o ZhR@sdZddlmZmZmZmZmZddlZddl m Z m Z m Z ddl mZmZmZmZddlmZmZmZmZmZmZmZmZmZmZmZmZmZddl m!Z!m"Z"m#Z#e#$e%Z&e"r^ddl'Z'Gd d d e Z(d gZ)dS) z Image processor class for LLaVa.)DictListOptionalTupleUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availableloggingc$s<eZdZdZdgZdddejddddddddf deded ee e e fd ed ed ee e e fd ede e e fdedee e ee fdee e ee fdeddffdd Z   d#dejde e ee e e ffdee e efdee e efdejf ddZejddfdejd e e e fd edee e efdee e efdejf ddZdddddddddddddejdfdedeedeed ee e e fd eed eed ee d eedee deedee e ee fdee e ee fdeed ee e efdeedee e efdejjf"d!d"ZZS)$LlavaImageProcessora Constructs a LLaVa image processor. Args: do_pad (`bool`, *optional*, defaults to `False`): Whether to pad the image to a square based on the longest edge. The padding value is determined by the `image_mean` parameter. Can be overridden by `do_pad` in the `preprocess` method. 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 `{"shortest_edge": 224}`): Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. 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_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image to the specified `crop_size`. Can be overridden by `do_center_crop` in the `preprocess` method. crop_size (`Dict[str, int]` *optional*, defaults to 224): Size of the output image after applying `center_crop`. Can be overridden by `crop_size` 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. Can be overridden by `do_normalize` in the `preprocess` method. image_mean (`float` or `List[float]`, *optional*, defaults to `[0.48145466, 0.4578275, 0.40821073]`): 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 `[0.26862954, 0.26130258, 0.27577711]`): 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_valuesFTNgp?do_pad do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  stjd i| |dur|nddi}t|dd}|dur|nddd}t|ddd}||_||_||_||_||_||_||_ ||_ | |_ | durL| nt |_ | durU| nt|_| |_gd |_dS) N shortest_edgeF)default_to_square)heightwidthTr&)r0 param_name)imagesr!r"r#r$r%r&r'r(r)r*r+r,return_tensors data_formatinput_data_format)super__init__r r!r"r#r$r%r&r'r(r)rr*rr+r,_valid_processor_keys)selfr!r"r#r$r%r&r'r(r)r*r+r,kwargs __class__r8_/var/www/auris/lib/python3.10/site-packages/transformers/models/llava/image_processing_llava.pyr:bs$ zLlavaImageProcessor.__init__rimagebackground_colorr6r7c Cst||\}}|tjkr|jdn|jd}||kr*|dur&t|||}|S|}|St||}t|tr8|g}nt||krFt d|d|tjkrt j |||f|j d} t |D]\} } | | | ddddf<qZ||kr||d} || dd| | |ddf<nd||d} || dddd| | |f<nNt j |||f|j d} t |D]\} } | | dddd| f<q||kr||d} || | | |ddddf<n||d} || dd| | |ddf<|durt| ||}|S| }|S)a Pads an image to a square based on the longest edge. Args: image (`np.ndarray`): The image to pad. background_color (`int` or `Tuple[int, int, int]`, *optional*, defaults to 0): The color to use for the padding. Can be an integer for single channel or a tuple of integers representing for multi-channel images. If passed as integer in mutli-channel mode, it will default to `0` in subsequent channels. data_format (`str` or `ChannelDimension`, *optional*): 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. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for 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. If unset, will use the inferred format of the input image. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rrFIRSTshapermax isinstanceintlen ValueErrornpZzerosrD enumerate) r<rArBr6r7r1r2Z num_channelsZmax_dimresulticolorstartr8r8r@ pad_to_squaresP             z!LlavaImageProcessor.pad_to_squarec Ksnd}d|vr |d}d}nd|vrd|vr|d|df}ntdt||||d}t|f||||d|S) aZ Resize an image. The shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output image. 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. Tr.Fr1r2zASize must contain either 'shortest_edge' or 'height' and 'width'.)r#r0r7)r#r$r6r7)rLr r ) r<rAr#r$r6r7r=r0Z output_sizer8r8r@r s.zLlavaImageProcessor.resizer4r5c Ks8|dur|n|j}|dur|n|j}|dur|n|j}t|ddd}|dur(|n|j}|dur1|n|j}|dur:|n|j}t|ddd}|durJ|n|j}| durS| n|j} | dur\| n|j } | dure| n|j } | durn| n|j } | durw| n|j } t ||jdt|}t|stdt|| | | | |||||d | rd d |D}d d |D}t|d r|rtd|durt|d }g}|D]K}|r|j|tdd|j D|d}|r|j||||d}|r|j|||d}|r|j|| |d}| r|j|| | |d}t|||d}||qt d|i|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_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image to a square based on the longest edge. The padding value is determined by the `image_mean` parameter. 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. Shortest edge of the image is resized to size["shortest_edge"], with the longest edge resized to keep the input aspect ratio. 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_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 center crop. Only has an effect if `do_center_crop` 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`. 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.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. Nr#F)r3r0r&T)Zcaptured_kwargsZvalid_processor_keyszkInvalid 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"r#r$cSg|]}t|qSr8)r .0rAr8r8r@ z2LlavaImageProcessor.preprocess..cSrTr8)rrUr8r8r@rWrXrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.css|] }t|dVqdS)N)rJ)rVxr8r8r@ sz1LlavaImageProcessor.preprocess..)rArBr7)rAr#r$r7)rAr#r7)rAscaler7)rAmeanZstdr7)Zinput_channel_dimr )dataZ tensor_type)!r!r"r#r r$r%r&r'r(r)r*r+r,rkeysr;rrrLrrloggerZ warning_oncerrStupler Z center_cropZrescale normalizerappendr )r<r4r!r"r#r$r%r&r'r(r)r*r+r,r5r6r7r=Zprocessed_imagesrAr8r8r@ preprocesss|J   zLlavaImageProcessor.preprocess)rNN)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBICUBICboolrrstrrJrfloatrr:rMZndarrayrrarrayrSr rFrrPILZImagerd __classcell__r8r8r>r@r5s*     8 S  4     r)*rhtypingrrrrrnumpyrMZimage_processing_utilsrr r Zimage_transformsr r r rZ image_utilsrrrrrrrrrrrrrutilsrrrZ get_loggerrer`rmr__all__r8r8r8r@s<