`iX |dZddlmZddlmZmZddlZddlm Z m Z m Z ddl m Z mZmZmZmZddlmZmZmZmZmZmZmZmZmZmZdd lmZmZm Z m!Z!e rddl"Z"e!j#e$Z%d e&e&efd Z' dd ej(de)deee*efd e+e)e)ffdZ,Gdde Z-dgZ.dS)zImage processor class for TVP.)Iterable)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict) PaddingModeflip_channel_orderpadresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingreturncjt|ttfr?t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/tvp/image_processing_tvp.py make_batchedr%5s&4-((Zq D%=-Q-QVdeklmenopeqVrVr FT5M * *~fQi/H/Hx   z B&BB C CC input_imagemax_sizeinput_data_formatct||\}}||kr|dz|z }|}||z}n|dz|z }|}||z}t|t|f}|S)Ng?)rint) r(r)r*heightwidthratio new_height new_widthsizes r$get_resize_output_image_sizer3Bsx #;0ABBMFE  f$ &  u$ &  OOS^^ ,D Kr&c+eZdZdZdgZddejdddddddejddddfde de e e e fd ed e d e e e e fd e d ee efde de e e e fdeeeefdede de de eeeefde eeeefddf fd Zejddfdejde e e fd ede ee efde ee efdejf dZddejddfdejde e e e fdeeeefdede ee efde ee eff dZdddddddddddddddejdfdede e de e e e fd e ed e e d e e e e fd e e d e ede de e e e fde eeeefde ede e de e de eeeefde eeeefde ede ee efdejf&dZeddddddddddddddddejdfdeeeeeeefde e de e e e fd e ed e e d e e e e fd e e d e ede e de e e e fde eeeefde ede e de e de eeeefde eeeefde ee efdede ee efdejjf(d ZxZ S)!TvpImageProcessora Constructs a Tvp 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 `{"longest_edge": 448}`): Size of the output image after resizing. The longest edge of the image will be resized to `size["longest_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": 448, "width": 448}`): 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_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image. Can be overridden by the `do_pad` parameter in the `preprocess` method. pad_size (`dict[str, int]`, *optional*, defaults to `{"height": 448, "width": 448}`): Size of the image after applying the padding. Can be overridden by the `pad_size` parameter in the `preprocess` method. constant_values (`Union[float, Iterable[float]]`, *optional*, defaults to 0): The fill value to use when padding the image. pad_mode (`PaddingMode`, *optional*, defaults to `PaddingMode.CONSTANT`): Use what kind of mode in padding. do_normalize (`bool`, *optional*, defaults to `True`): Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess` method. do_flip_channel_order (`bool`, *optional*, defaults to `True`): Whether to flip the color channels from RGB to BGR. Can be overridden by the `do_flip_channel_order` 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?r do_resizer2resampledo_center_crop crop_size do_rescalerescale_factordo_padpad_sizeconstant_valuespad_mode do_normalizedo_flip_channel_order image_mean image_stdrc dtjdi|||nddi}||nddd}| | nddd} ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||nt|_||nt"|_dS)N longest_edger')r-r.)super__init__r7r2r9r:r8r;r<r=r>r?r@rArBrrCrrD)selfr7r2r8r9r:r;r<r=r>r?r@rArBrCrDkwargs __class__s r$rIzTvpImageProcessor.__init__s& ""6"""'ttnc-B!*!6IIsUX**DZ&/&;AVr&image data_formatr*c t|d}d|vrd|vr|d|df}n@d|vrt||d|}n$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 `{"longest_edge": s}`, the output image will have its longest 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. Fdefault_to_squarer-r.rFzCSize must have 'height' and 'width' or 'longest_edge' as keys. Got )r2r8rNr*)r r3r"keysr )rJrMr2r8rNr*rK output_sizes r$r zTvpImageProcessor.resizes4TU;;; t  4>4=9KK t # #6ud>>RTeffKKpcgclclcncnppqq q  #/       r&c t||\}} |d|} |d| } | | z | |z } } | dks| dkrtdd| fd| ff}t||||||}|S)a+ Pad an image with zeros to the given size. Args: image (`np.ndarray`): Image to pad. pad_size (`dict[str, int]`) Size of the output image with pad. constant_values (`Union[float, Iterable[float]]`) The fill value to use when padding the image. pad_mode (`PaddingMode`) The pad mode, default to PaddingMode.CONSTANT data_format (`ChannelDimension` or `str`, *optional*) The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. ) channel_dimr-r.rz0The padding size must be greater than image size)moder?rNr*)rgetr"r )rJrMr>r?r@rNr*rKr-r. max_height max_width pad_right pad_bottompadding padded_images r$ pad_imagezTvpImageProcessor.pad_images6'u:KLLL \\(F33 LL%00 )E 1:3F: q==JNNOPP Pz?Q N3  +#/    r&c t||| ||||||| t|}|r|||||}|r||||}|r||||}| r6||tj|||}| r| || | | |}|rt||}t|||}|S) zPreprocesses a single image.) r;r<rArCrDr9r:r7r2r8)rMr2r8r*)r2r*)rMscaler*)rMmeanstdr*)rMr>r?r@r*)rMr*)input_channel_dim) rrr center_croprescale normalizeastypenpfloat32r^r r)rJrMr7r2r8r9r:r;r<r=r>r?r@rArBrCrDrNr*rKs r$_preprocess_imagez#TvpImageProcessor._preprocess_image sQ0 &!)%!) u%%  pKKe$]nKooE  a$$UN_$``E  iLLuNVgLhhE  NNll2:..ZYbs#E  NN! /!"3 #E ! Y&UFWXXXE+E;Rcddd r&r#return_tensorscv njnjnjnjnj  nj  nj  nj r nj  nj nj nj nj nj tdnjtdt!|st#dt%|}   fd|D}d|i}t'|| S) a9 Preprocess an image or batch of images. Args: videos (`ImageInput` or `list[ImageInput]` or `list[list[ImageInput]]`): Frames to preprocess. 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_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image. Can be overridden by the `do_pad` parameter in the `preprocess` method. pad_size (`dict[str, int]`, *optional*, defaults to `{"height": 448, "width": 448}`): Size of the image after applying the padding. Can be overridden by the `pad_size` parameter in the `preprocess` method. constant_values (`Union[float, Iterable[float]]`, *optional*, defaults to 0): The fill value to use when padding the image. pad_mode (`PaddingMode`, *optional*, defaults to "PaddingMode.CONSTANT"): Use what kind of mode in padding. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the image. do_flip_channel_order (`bool`, *optional*, defaults to `self.do_flip_channel_order`): Whether to flip the channel order of 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. NFrPr:) param_namezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.crg|]3}tj fd|D4S)c^g|])}|    *S))rMr7r2r8r9r:r;r<r=r>r?r@rArBrCrDrNr*)rj).0imgr?r:rNr9rBrAr=r;r7rCrDr*r@r>r8r<rJr2s r$ z;TvpImageProcessor.preprocess...sv*)**!"+!!)'5"+#-'5%!)(7!)%1.C#-"+$/*;%+r&)rharray)rpvideor?r:rNr9rBrAr=r;r7rCrDr*r@r>r8r<rJr2s r$rrz0TvpImageProcessor.preprocess..s   43 H* %+     r&r6)data tensor_type)r7r8r9r;r<r=r>r?r@rArBrCrDr2r r:rr"r%r)rJr#r7r2r8r9r:r;r<r=r>r?r@rArBrCrDrkrNr*rus` ``````````````` `` r$ preprocesszTvpImageProcessor.preprocessRs `"+!6IIDN '388+9+E4K^#-#9ZZt +9+E4K^!-4;'388-<-H//dNb':88T]'3'?||TEV %:%F ! !DLf $.#9ZZt !*!6IIDN 'ttTYTU;;;!*!6IIDN !) DDD F## :  f%%                     4 5   :'>BBBBr&)!__name__ __module__ __qualname____doc__model_input_namesrBILINEARr CONSTANTboolrdictstrr,rfloatrr rIrhndarrayrr r^FIRSTrrjrrPILImagerw __classcell__)rLs@r$r5r5Us//b(()-'9'B#.2,3-19: + 4!&*:>9=!&W&W&WtCH~&&W% &W  &W DcN+ &W&Wc5j)&W&W4S>*&Wuhuo56&W&W&W $&WU5$u+#567&W E%e"456!&W$ %&W&W&W&W&W&WX(:'B>BDH ) ) z) 38n) % ) eC)9$9:; ) $E#/?*?$@A )  ) ) ) ) \.29: + 4>BDH--z-4S>*-uhuo56 -  - eC)9$9:; -$E#/?*?$@A----d%))-15)-.2%)*.-1CG*.'+04:>9=2B2HDH'EEED>EtCH~& E -. E ! EDcN+ETNE!EE4S>*E"%x(>"?@E;'EtnE (~E U5$u+#567!E"E%e"456#E$./%E&$E#/?*?$@A'E* +EEEEN%$&&%))-15)-.2%)*.!%-1CG*.'+04:>9=;?(8(>DH)JCJCj$z"2Dj9I4JJKJCD>JCtCH~& JC -. JC ! JCDcN+JCTNJC!JCJC4S>*JC"%x(>"?@JC;'JCtnJC (~JC U5$u+#567!JC"E%e"456#JC$!sJ!78%JC&&'JC($E#/?*?$@A)JC* +JCJCJC'&JCJCJCJCJCr&r5)r'N)/r{collections.abcrtypingrrnumpyrhimage_processing_utilsrrr image_transformsr r r r r image_utilsrrrrrrrrrrutilsrrrrr get_loggerrxloggerr r%rr,rr!r3r5__all__rGr&r$rsI%$$$$$$$""""""""UUUUUUUUUU                        _^^^^^^^^^^^JJJ  H % % DDj!12 D D D D@D c+;&; <= 38_ &HCHCHCHCHC*HCHCHCV  r&