`iAHdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd lm Z erddl!Z!ej"e#Z$d e%e%efd Z&e d GddeZ'dgZ(dS)z#Image processor class for VideoMAE.)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requiresreturncjt|ttfr?t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/videomae/image_processing_videomae.py make_batchedr$3s&4-((Zq D%=-Q-QVdeklmenopeqVrVr FT5M * *~fQi/H/Hx   z B&BB C CC)vision)backendsc!eZdZdZdgZddejdddddddf dedee e e fded ed ee e e fd ed e e e fd edee e ee fdee e ee fddffd Zejddfdejde e e fdedee e efdee e efdejf dZddddddddddejdf dedeedee e e fdeed eed ee e e fd eed ee d eedee e ee fdee e ee fdeedee e efdejfdZedddddddddddejdf dedeedee e e fdeed eed ee e e fd eed ee d eedee e ee fdee e ee fdee e efdedee e efdejjfdZxZS)VideoMAEImageProcessorap Constructs a VideoMAE 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[str, int]` *optional*, defaults to `{"shortest_edge": 224}`): Size of the output image after resizing. The shortest edge of the image will be resized to `size["shortest_edge"]` while maintaining the aspect ratio of the original image. Can be overridden by `size` 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_center_crop (`bool`, *optional*, defaults to `True`): Whether to center crop the image to the specified `crop_size`. Can be overridden by the `do_center_crop` parameter in the `preprocess` method. crop_size (`dict[str, int]`, *optional*, defaults to `{"height": 224, "width": 224}`): Size of the image after applying the center crop. Can be overridden by the `crop_size` 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`): Defines the 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. pixel_valuesTNgp? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factor do_normalize image_mean image_stdrc  Ptjdi| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | nt|_dS) N shortest_edgeFdefault_to_square)heightwidthr/ param_name)super__init__rr+r,r.r/r-r0r1r2r r3r r4) selfr+r,r-r.r/r0r1r2r3r4kwargs __class__s r#r@zVideoMAEImageProcessor.__init__is ""6"""'ttos-CTU;;;!*!6IIsUX**DZ&/&;AVr%image data_formatinput_data_formatc t|d}d|vrt||dd|}n=d|vrd|vr|d|df}n$td|t |f||||d|S) a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will have the size `(h, w)`. If `size` is of the form `{"shortest_edge": s}`, the output image will have its shortest edge of length `s` while keeping the aspect ratio of the original image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): 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 (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fr8r6)r9rFr:r;zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r,r-rErF)rr r!keysr )rArDr,r-rErFrB output_sizes r#r zVideoMAEImageProcessor.resizes4TU;;; d " "6tO,YjKK  'T//>4=9KKqdhdmdmdodoqqrr r  #/       r%c t||| | | ||||| t|}|r)t|rtd| t |} |r||||| }|r|||| }|r|||| }| r| || | | }t|| | }|S) zPreprocesses a single image.) r0r1r2r3r4r.r/r+r,r-zIt 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.N)rDr,r-rF)r,rF)rDscalerF)rDmeanstdrF)input_channel_dim) rrrlogger warning_oncerr center_croprescale normalizer )rArDr+r,r-r.r/r0r1r2r3r4rErFs r#_preprocess_imagez(VideoMAEImageProcessor._preprocess_images8" &!)%!) u%%  /%00    s     $ >u E E   pKKe$]nKooE  a$$UN_$``E  iLLuNVgLhhE  uNNZYbsNttE+E;Rcddd r%r"return_tensorsc  njnjnjnjnj  nj  nj  nj njtdnj tdt|stdt|}   f d|D}d|i}t|| S) aH 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 applying resize. resample (`PILImageResampling`, *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_centre_crop`): Whether to centre crop the image. crop_size (`dict[str, int]`, *optional*, defaults to `self.crop_size`): Size of the image after applying the centre crop. 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the inferred 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. NFr8r/r<zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.cD g|]} f d|DS)cT g|]$} |    %S)) rDr+r,r-r.r/r0r1r2r3r4rErF)rT).0imgr/rEr.r2r0r+r3r4rFr-r1rAr,s r# z@VideoMAEImageProcessor.preprocess...Esg    &&'%#1')#1!-)' +&7'   r%r>)rYvideor/rEr.r2r0r+r3r4rFr-r1rAr,s r#r[z5VideoMAEImageProcessor.preprocess..Ds   &%                 !!      r%r*)data tensor_type)r+r-r.r0r1r2r3r4r,rr/rr!r$r)rAr"r+r,r-r.r/r0r1r2r3r4rUrErFr]s` `````````` `` r# preprocessz!VideoMAEImageProcessor.preprocesssB"+!6IIDN '388+9+E4K^#-#9ZZt +9+E4K^'3'?||TEV #-#9ZZt !*!6IIDN 'ttTYTU;;;!*!6IIDN !) DDD F## :  f%%                & '   ,'>BBBBr%)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrintrfloatrr@npndarrayrr FIRSTrrTrrPILImager_ __classcell__)rCs@r#r)r)@s##J(()-'9'B#.2,3!:>9=WWWtCH~&W% W  W DcN+ WWc5j)WWU5$u+#567WE%e"456W WWWWWWF(:'B>BDH * * z* 38n* % * eC)9$9:; * $E#/?*?$@A *  * * * * ^%))-15)-.2%)*.'+:>9=2B2HDH777D>7tCH~& 7 -. 7 ! 7DcN+7TN7!7tn7U5$u+#5677E%e"4567./7$E#/?*?$@A7 7777r%$&&%))-15)-.2%)*.'+:>9=;?(8(>DHmCmCmCD>mCtCH~& mC -. mC ! mCDcN+mCTNmC!mCtnmCU5$u+#567mCE%e"456mC!sJ!78mC&mC$E#/?*?$@AmC !mCmCmC'&mCmCmCmCmCr%r)))rctypingrrnumpyrkimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrutilsrrrrutils.import_utilsrrn get_loggerr`rOrr$r)__all__r>r%r#rzs*)""""""""UUUUUUUUUU                          _^^^^^^^^^^^******JJJ  H % % DDj!12 D D D D ;ZCZCZCZCZC/ZCZC ZCz $ $r%