o iB@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd l m!Z!e"e#Z$er\ddl%Z%e!d d Gd d d eZ&d gZ'dS)zImage processor class for CLIP.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbget_resize_output_image_sizeresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_kwargsvalidate_preprocess_arguments) TensorTypeis_vision_availablelogging)requires)vision)backendsc"seZdZdZdgZddejddddddddf dedee e e fded ed ee e e fd ed e e e fd edee e ee fdee e ee fdeddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZddddddddddddejdfdedeedee e e fdeed eed ee d eed ee d eedee e ee fdee e ee fdeedee e efdeedee e efdejjf ddZZS)CLIPImageProcessora Constructs a CLIP 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 `{"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_valuesTNgp? 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}||_||_||_||_||_||_||_ ||_ | durI| nt |_ | durR| nt |_| |_gd |_d | vrv| d rx|d|dd|_t|d dSdSdS) N shortest_edgeF)default_to_square)heightwidthTr$)r. param_name)imagesr r!r"r#r$r%r&r'r(r)r*return_tensors data_formatinput_data_formatuse_square_size)super__init__rr r!r"r#r$r%r&r'r r(r r)r*_valid_processor_keysdelattr) selfr r!r"r#r$r%r&r'r(r)r*kwargs __class__r7b/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.pyr9_s*  zCLIPImageProcessor.__init__imager4r5c 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,Fr/r0zASize must contain either 'shortest_edge' or 'height' and 'width'.)r!r.r5)r!r"r4r5) ValueErrorr r ) r<rAr!r"r4r5r=r. output_sizer7r7r@r s.zCLIPImageProcessor.resizer2r3c s|dur|n|j}|dur|n|j}t|ddd}|dur|n|j}|dur(|n|j}|dur1|n|j}t|ddd}|durA|n|j}|durJ|n|j}| durS| n|j} | dur\| n|j } | dure| n|j } | durn| n|j } t | |jd||}t|}t|stdt||| | | |||||d | rd d |D}d d |D}|rt|d rtddurt|d g}|D]1}|r|j|||d}|r|j||d}|r|j||d}| r|j|| | d}||qćfdd |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. 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)r1r.r$T)captured_kwargsvalid_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$r r!r"cSg|]}t|qSr7)r.0rAr7r7r@ 6z1CLIPImageProcessor.preprocess..cSrFr7)rrGr7r7r@rI9rJrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rAr!r"r5)rAr!r5)rAscaler5)rAmeanstdr5csg|] }t|dqS))input_channel_dim)r rGr4r5r7r@rIVs r)data tensor_type)r r!rr"r#r$r%r&r'r(r)r*rkeysr: fetch_imagesrrrBrrlogger warning_oncerr center_croprescale normalizeappendr)r<r2r r!r"r#r$r%r&r'r(r)r*r3r4r5r= all_imagesrArPr7rOr@ preprocesssvF      zCLIPImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrintrfloatlistr9npndarrayrr FIRSTrrPILImager[ __classcell__r7r7r>r@r5s&     >  4     r)(r_typingrrnumpyrhimage_processing_utilsrrrimage_transformsrr r r image_utilsr r rrrrrrrrrrutilsrrrutils.import_utilsr get_loggerr\rTrkr__all__r7r7r7r@s 8   +