sgp1dZddlmZmZmZmZmZmZerddlm Z ddl Z ddl Z ddlmZmZddlmZmZddlmZmZmZmZmZmZmZmZmZmZdd lm Z m!Z!m"Z"m#Z#erddl$Z$e"jJe&Z'Gd d eZ(y) zImage processor class for GLPN.) TYPE_CHECKINGDictListOptionalTupleUnion)DepthEstimatorOutputN)BaseImageProcessor BatchFeature)resizeto_channel_dimension_format) ChannelDimensionPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imageis_torch_availablemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingrequires_backendsceZdZdZdgZddej dfdedededd ffd Z ej d d fd e jded ed e e de eee fde jf dZed d d d d e j$d fdedeedeefde ede ede ede eeefd e de eee fdefdZ dddde eeeeeefd fdeeeeffdZxZS)GLPNImageProcessora Constructs a GLPN image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to resize the image's (height, width) dimensions, rounding them down to the closest multiple of `size_divisor`. Can be overridden by `do_resize` in `preprocess`. size_divisor (`int`, *optional*, defaults to 32): When `do_resize` is `True`, images are resized so their height and width are rounded down to the closest multiple of `size_divisor`. Can be overridden by `size_divisor` in `preprocess`. resample (`PIL.Image` resampling filter, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`. do_rescale (`bool`, *optional*, defaults to `True`): Whether or not to apply the scaling factor (to make pixel values floats between 0. and 1.). Can be overridden by `do_rescale` in `preprocess`. pixel_valuesT do_resize size_divisor do_rescalereturnNc \||_||_||_||_t |di|y)N)r!r#r"resamplesuper__init__)selfr!r"r'r#kwargs __class__s a/var/www/html/venv/lib/python3.12/site-packages/transformers/models/glpn/image_processing_glpn.pyr)zGLPNImageProcessor.__init__Fs2#$(   "6"imager' data_formatinput_data_formatc lt||\}}||z|z} ||z|z} t|| | ff|||d|}|S)a* Resize the image, rounding the (height, width) dimensions down to the closest multiple of size_divisor. If the image is of dimension (3, 260, 170) and size_divisor is 32, the image will be resized to (3, 256, 160). Args: image (`np.ndarray`): The image to resize. size_divisor (`int`): The image is resized so its height and width are rounded down to the closest multiple of `size_divisor`. resample: `PIL.Image` resampling 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 `None`, the channel dimension format of the input image is used. Can be one of: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not set, 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. Returns: `np.ndarray`: The resized image. ) channel_dim)r'r0r1)rr ) r*r/r"r'r0r1r+heightwidthnew_hnew_ws r-r zGLPNImageProcessor.resizeTsiH'u:KL ,&5% 4  EN #/     r.imageszPIL.Image.Imagereturn_tensorsc ||n |j}||n |j}||n |j}||n |j}t |}t |s t dt||||D cgc] } t| }} t|dr|rtjd|t|d}|r"|D cgc]} |j| |||}} |r!|D cgc]} |j| d|}} |D cgc]} t| ||}} d |i} t!| | Scc} wcc} wcc} wcc} w) a Preprocess the given images. Args: images (`PIL.Image.Image` or `TensorType` or `List[np.ndarray]` or `List[TensorType]`): Images 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_normalize=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the input such that the (height, width) dimensions are a multiple of `size_divisor`. size_divisor (`int`, *optional*, defaults to `self.size_divisor`): When `do_resize` is `True`, images are resized so their height and width are rounded down to the closest multiple of `size_divisor`. resample (`PIL.Image` resampling filter, *optional*, defaults to `self.resample`): `PIL.Image` resampling 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 or not to apply the scaling factor (to make pixel values floats between 0. and 1.). return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - `None`: 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) 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. zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r!sizer'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.)r"r'r1gp?)scaler1)input_channel_dimr)data tensor_type)r!r#r"r'rr ValueErrorrrrlogger warning_oncerr rescalerr ) r*r8r!r"r'r#r9r0r1imgr/r>s r- preprocesszGLPNImageProcessor.preprocesss^"+!6IDNN #-#9Zt '3'?|TEVEV '38$V,F#:  & 288#.%88 6!9 %*   s   $ >vay I  $ E xct uF kqrbgdll5K\l]rFrou ej '{N_ `  '>BB59 s s4D0D5'D:D?outputsr target_sizesc~t|d|j}|"t|t|k7r tdg}|dgt|zn|}t ||D]\\}}|B|d}t j jj||dd}|j}|jd|i^|S) a Converts the raw output of [`DepthEstimatorOutput`] into final depth predictions and depth PIL images. Only supports PyTorch. Args: outputs ([`DepthEstimatorOutput`]): Raw outputs of the model. target_sizes (`TensorType` or `List[Tuple[int, int]]`, *optional*): Tensor of shape `(batch_size, 2)` or list of tuples (`Tuple[int, int]`) containing the target size (height, width) of each image in the batch. If left to None, predictions will not be resized. Returns: `List[Dict[str, TensorType]]`: A list of dictionaries of tensors representing the processed depth predictions. torchNz]Make sure that you pass in as many target sizes as the batch dimension of the predicted depth)NN.bicubicF)r;mode align_cornerspredicted_depth) rrMlenr@ziprInn functional interpolatesqueezeappend)r*rFrGrMresultsdepth target_sizes r-post_process_depth_estimationz0GLPNImageProcessor.post_process_depth_estimations( $(!11  $3+?3|CT+To 8D8LvO 44R^ "%o|"D 7 E;&o.++77KV_ot7u  NN-u5 6  7r.)N)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolintr)npndarrayrrrstrr rFIRSTrrr rErrrX __classcell__)r,s@r-rr2s"((#,, # # #  #  #$(:'B'B26DH 0zz00% 0 ./ 0 $E#/?*?$@A 0 0d%&%)&*%);?(8(>(>DH^C'T:K5LdS]N^^_^CD>^Csm ^C TN ^C!z3!78^C&^C$E#/?*?$@A^C ^C'^CFRV'''uZeCHo1F%LMN' d3 ?# $ 'r.r))r\typingrrrrrrmodeling_outputsr numpyra PIL.ImagePILimage_processing_utilsr r image_transformsr r image_utilsrrrrrrrrrrutilsrrrrrI get_loggerrYrArr&r.r-rpsj&DD8FC   ]\   H %\+\r.