o i>@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd l m!Z!erWddl"Z"e#e$Z%e!d d Gd d d eZ&d gZ'dS)z#Image processor class for ConvNeXT.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict) center_cropget_resize_output_image_sizeresizeto_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_availablelogging)requires)vision)backendscseZdZdZdgZdddejdddddf dedee e e fdee d ed ed e e e fd ed ee e ee fdee e ee fddffdd Zejddfdejde e e fde d edee e efdee e efdejfddZeddddddddddejdf dedeedee e e fdee d eed eed ee d eed ee e ee fdee e ee fdee e efdedee e efdejjfddZZS)ConvNextImageProcessora; Constructs a ConvNeXT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Controls 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": 384}`): Resolution of the output image after `resize` is applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. Can be overridden by `size` in the `preprocess` method. crop_pct (`float` *optional*, defaults to 224 / 256): Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size < 384. Can be overridden by `crop_pct` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): 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. 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. 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. pixel_valuesTNgp? do_resizesizecrop_pctresample do_rescalerescale_factor do_normalize image_mean image_stdreturnc  stjdi| |dur|nddi}t|dd}||_||_|dur%|nd|_||_||_||_||_ |dur:|nt |_ | durF| |_ dSt |_ dS)N shortest_edgeFdefault_to_squareg?)super__init__rr r!r"r#r$r%r&r r'r r() selfr r!r"r#r$r%r&r'r(kwargs __class__r.j/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/convnext/image_processing_convnext.pyr0[s  zConvNextImageProcessor.__init__image data_formatinput_data_formatc Kst|dd}d|vrtd||d}|dkrDt||} t|| d|d} td || |||d|}td |||f||d|St|f||f|||d |S) a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary of the form `{"shortest_edge": int}`, specifying the size of the output image. If `size["shortest_edge"]` >= 384 image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"] / crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. crop_pct (`float`): Percentage of the image to crop. Only has an effect if size < 384. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): Resampling filter to use when resizing 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 from the input image. Fr,r*z6Size dictionary must contain 'shortest_edge' key. Got r+)r!r-r8)r6r!r#r7r8)r6r!r7r8)r!r#r7r8Nr.)r ValueErrorkeysintr r r) r1r6r!r"r#r7r8r2r*resize_shortest_edge resize_sizer.r.r5r wsH    zConvNextImageProcessor.resizeimagesreturn_tensorsc s|dur|nj}durnjdurnj|dur!|nj}dur*nj|dur3|nj}dur<njdurEnjdurNnjt ddt |}t |sct dt |||ddd|D}|rt|drtd durt|d|rfd d|D}|rfd d|D}|rfd d|D}fd d|D}d|i}t|| dS)aW 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 output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. crop_pct (`float`, *optional*, defaults to `self.crop_pct`): Percentage of the image to crop if size < 384. resample (`int`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of `PILImageResampling`, filters. 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. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation. 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.)r$r%r&r'r(r r!r#cSsg|]}t|qSr.)r.0r6r.r.r5 sz5ConvNextImageProcessor.preprocess..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.c s g|] }j|dqS))r6r!r"r#r8)r r@)r"r8r#r1r!r.r5rB*s  csg|] }j|dqS))r6scaler8)rescaler@)r8r%r1r.r5rB2scsg|] }j|dqS))r6meanstdr8) normalizer@)r'r(r8r1r.r5rB8scsg|] }t|dqS))input_channel_dim)r r@)r7r8r.r5rB=sr)data tensor_type)r r"r#r$r%r&r'r(r!rrrr9rrlogger warning_oncerr)r1r>r r!r"r#r$r%r&r'r(r?r7r8rIr.) r"r7r'r(r8r#r%r1r!r5 preprocesssbA     z!ConvNextImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrr;floatrlistr0BICUBICnpndarrayrr rFIRSTrrPILImagerM __classcell__r.r.r3r5r4s#    !  E     r)(rQtypingrrnumpyrZimage_processing_utilsrrrimage_transformsrr r r image_utilsr r rrrrrrrrrutilsrrrrutils.import_utilsrr] get_loggerrNrKr__all__r.r.r.r5s 4