o i;@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZerOddlZe e!Z"Gd d d eZ#d gZ$dS) zImage processor class for BLIP.)OptionalUnionN)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_availableloggingcseZdZdZdgZddejddddddf dedee e e fded ed e e e fd ed ee e ee fd ee e ee fdeddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZeddddddddddejdf dedeedee e e fdeed eed ee d eed ee e ee fd ee e ee fdee e efdeededee e efdejjfddZZS)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  stjdi| |dur|nddd}t|dd}||_||_||_||_||_||_|dur2|nt |_ |dur;|nt |_ | |_ dS)Ni)heightwidthTdefault_to_square)super__init__rrrrrr r!r r"r r#r$) selfrrrrr r!r"r#r$kwargs __class__r*b/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/blip/image_processing_blip.pyr,Ss   zBlipImageProcessor.__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.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 )rrr3r4)r ValueErrorkeysr )r-r2rrr3r4r. output_sizer*r*r1r os#zBlipImageProcessor.resizeimagesreturn_tensorsc s|dur|nj}durnj|dur|nj}dur!nj|dur*|nj}dur3njdur<nj| durE| nj} durNnjt dd |}t |}t |sht dt|||d| r}dd|D}dd|D}|rt|d rtd durt|d |rfd d|D}|rfd d|D}|rćfd d|D}fdd|D}td|i| d}|S)am 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.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. NFr(zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rr r!r"r#rrrcSg|]}t|qSr*)r.0r2r*r*r1 z1BlipImageProcessor.preprocess..cSr:r*)rr;r*r*r1r=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.csg|] }j|dqS))r2rrr4)r r;)r4rr-rr*r1r=csg|] }j|dqS))r2scaler4)rescaler;)r4r r-r*r1r=scsg|] }j|dqS))r2meanstdr4) normalizer;)r"r#r4r-r*r1r=r?csg|] }t|dqS))input_channel_dim)r r;)r3r4r*r1r= sr)data tensor_type)rrrr r!r"r#r$rr fetch_imagesrrr5rrlogger warning_oncerr)r-r8rrrrr r!r"r#r9r$r3r4encoded_outputsr*)r3r"r#r4rr r-rr1 preprocesssh@     zBlipImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrintrfloatlistr,npndarrayr r rFIRSTrrPILImagerL __classcell__r*r*r/r1r.s"       0     r)%rPtypingrrnumpyrYimage_processing_utilsrrrimage_transformsrr r image_utilsr r r rrrrrrrrutilsrrrrr\ get_loggerrMrIr__all__r*r*r*r1s4   |