o iq8@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd lmZe e!Z"ed d Gd d d eZ#d gZ$dS)zImage processor class for ViT.)OptionalUnionN)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_kwargslogging)requires)vision)backendscseZdZdZdgZddejddddddf dedee e e fded ed e e e fd ed ee e ee fd ee e ee fdeeddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZedddddddddejddf dedeedee e e fdeed eed ee d eed ee e ee fd ee e ee fdee e efde e efdee e efdeefddZZS)ViTImageProcessorax Constructs a ViT image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions to the specified `(size["height"], size["width"])`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `{"height": 224, "width": 224}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. 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. 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. 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. do_convert_rgb (`bool`, *optional*): 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|}||_||_||_||_||_||_|dur0|nt |_ |dur9|nt |_ | |_ dS)N)heightwidth)super__init__rrr!r#rr r"r r$r r%r&) selfrrr r!r"r#r$r%r&kwargs __class__r+`/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/vit/image_processing_vit.pyr-Os  zViTImageProcessor.__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.BILINEAR`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`. 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 )rr r4r5)r ValueErrorkeysr )r.r3rr r4r5r/ output_sizer+r+r2r is#zViTImageProcessor.resizeimagesreturn_tensorsc s|dur|nj}|dur|nj}|dur|nj}dur!njdur*njdur3njdur<nj| durE| nj} |durN|nj}t |t |}t |sat dt ||||d| rvdd|D}dd|D}|rt|drtddurt|d|rfd d|D}|rfd d|D}|rfd d|D}fd d|D}d |i}t|| dS)aa 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`): Dictionary in the format `{"height": h, "width": w}` specifying the size of the output image after resizing. resample (`PILImageResampling` filter, *optional*, defaults to `self.resample`): `PILImageResampling` filter to use if resizing the image e.g. `PILImageResampling.BILINEAR`. 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 use if `do_normalize` is set to `True`. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to use 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. NzkInvalid 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.0r3r+r+r2 z0ViTImageProcessor.preprocess..cSr;r+)rr<r+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.csg|] }j|dqS))r3rr r5)r r<)r5r r. size_dictr+r2r>csg|] }j|dqS))r3scaler5)rescaler<)r5r"r.r+r2r> scsg|] }j|dqS))r3meanstdr5) normalizer<)r$r%r5r.r+r2r>rAcsg|] }t|dqS))input_channel_dim)r r<)r4r5r+r2r>sr)data tensor_type)rr!r#r r"r$r%r&rrrrr6rrlogger warning_oncerr)r.r9rrr r!r"r#r$r%r:r4r5r&rHr+)r4r$r%r5r r"r.r@r2 preprocesssf?    zViTImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrintrfloatlistr-npndarrayr r rFIRSTrrrL __classcell__r+r+r0r2r+s       0     r)%rPtypingrrnumpyrYimage_processing_utilsrrrimage_transformsrr r image_utilsr r r rrrrrrrrutilsrrrutils.import_utilsr get_loggerrMrJr__all__r+r+r+r2s4   u