-i5Y pdZddlmZddlZddlmZmZmZddl m Z m Z m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZddlmZdd lmZmZmZm Z erddl!Z!e jDe#Z$Gd d ed Z%de&e&efdZ' ddejPde)de*ezdzde+e)e)ffdZ,GddeZ-dgZ.y)zImage processor class for TVP.)IterableN)BaseImageProcessor BatchFeature get_size_dict) PaddingModeflip_channel_orderpadresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplingget_image_sizeis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) ImagesKwargs) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingcHeZdZUdZeed<eeezdzed<edzed<y)TvpImageProcessorKwargsu do_flip_channel_order (`bool`, *optional*): Whether to flip the channel order of the image from RGB to BGR. constant_values (`float` or `List[float]`, *optional*): Value used to fill the padding area when `pad_mode` is `'constant'`. pad_mode (`str`, *optional*): Padding mode to use — `'constant'`, `'edge'`, `'reflect'`, or `'symmetric'`. do_flip_channel_orderNconstant_valuespad_mode) __name__ __module__ __qualname____doc__bool__annotations__floatliststrh/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/tvp/image_processing_tvp.pyrr3s- T%[(4//Djr+rF)totalreturnct|ttfr,t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancer(tupler ValueError)videoss r, make_batchedr4Cs&4-(Zq D%=-QVdeklmenopeqVr FT5M *~fQi/Hx  z 9&B CCr+ input_imagemax_sizeinput_data_formatct||\}}||k\r|dz|z }|}||z}n|dz|z }|}||z}t|t|f}|S)Ng?)rint) r5r6r7heightwidthratio new_height new_widthsizes r,get_resize_output_image_sizer@Psm #;0ABMFE  f$ &  u$ &  OS^ ,D Kr+c*eZdZdZdgZeZddejddddddde jddddfde de e efdzd ed e d e e efdzd e d eezde de e efdzdeeezde de de deeezdzdeeezdzddf fd Zejddfdej(de e efd ede ezdzde ezdzdej(f dZdde jddfdej(de e efdzdeeezde de ezdzde ezdzf dZdddddddddddddddej0dfdede dzde e efdzd edzd e dzd e e efdzd e dzd edzde de e efdzdeeezdzde dzde dzde dzdeeezdzdeeezdzdedzde ezdzdej(f&dZeddddddddddddddddej0dfdeeezeeezde dzde e efdzd edzd e dzd e e efdzd e dzd edzde dzde e efdzdeeezdzde dzde dzde dzdeeezdzdeeezdzde ezdzdede ezdzdej<j<f(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_resizer?resampledo_center_crop crop_size do_rescalerescale_factordo_padpad_sizerr do_normalizer image_mean image_stdr.c Vt|di|||nddi}||nddd}| | nddd} ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||nt|_|||_yt"|_y)N longest_edge)r:r;r*)super__init__rDr?rFrGrErHrIrJrKrr rLrr rMrrN)selfrDr?rErFrGrHrIrJrKrr rLrrMrNkwargs __class__s r,rSzTvpImageProcessor.__init__s& "6"'tnc-B!*!6IsUX*DZ&/&;AVr+image data_formatr7c t|d}d|vrd|vr |d|df}n1d|vrt||d|}ntd|jt |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;rPzCSize must have 'height' and 'width' or 'longest_edge' as keys. Got )r?rErXr7)rr@r2keysr )rTrWr?rErXr7rU output_sizes r,r zTvpImageProcessor.resizes4TU; t 4>4=9K t #6ud>>RTefKbcgclclcnbopq q  #/     r+c t||\}} |jd|} |jd| } | | z | |z } } | dks| dkr tdd| 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)moderrXr7)rgetr2r )rTrWrKrr rXr7rUr:r; max_height max_width pad_right pad_bottompadding padded_images r, pad_imagezTvpImageProcessor.pad_images6'u:KL \\(F3 LL%0 )E 1:3F: q=JNOP Pz?Q N3  +#/  r+c t||| ||||||| t|}|r|j||||}|r|j|||}|r|j |||}| r2|j |j tj|||}| r|j|| | | |}|r t||}t|||}|S) zPreprocesses a single image.) rHrIrLrMrNrFrGrDr?rE)rWr?rEr7)r?r7)rWscaler7)rWmeanstdr7)rWrKrr r7)rWr7)input_channel_dim) rrr center_croprescale normalizeastypenpfloat32rhr r )rTrWrDr?rErFrGrHrIrJrKrr rLrrMrNrXr7rUs r,_preprocess_imagez#TvpImageProcessor._preprocess_images0 &!)%!) u% KKe$]nKoE $$UN_$`E LLuNVgLhE NNll2::.ZYbs#E NN! /!"3 #E !&UFWXE+E;Rcd r+r3return_tensorsc6||n |j}||n |j}||n |j}||n |j}||n |j}| | n |j } | | n |j } | | n |j} | r| n |j} | | n |j} ||n |j}||n |j}||n |j}||n |j}t|d}||n |j}t|d}t!|s t#dt%|}|Dcgc]F}t'j(|Dcgc]%}|j+||||||||| | | | | |||||'c}H}}}d|i}t-||Scc}wcc}}w) a} 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.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.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. FrZrG) param_namezSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor)rWrDr?rErFrGrHrIrJrKrr rLrrMrNrXr7rC)data tensor_type)rDrErFrHrIrJrKrr rLrrMrNr?rrGrr2r4rrarrayrtr)rTr3rDr?rErFrGrHrIrJrKrr rLrrMrNrurXr7videoimgrxs r, preprocesszTvpImageProcessor.preprocessas\"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^!-4;;'38-<-H/dNbNb'8T]]'3'?|TEVEV %:%F !DLfLf $.#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F#rs sf%8 5 43 HH, %+*)**!"+!!)'5"+#-'5%!)(7!)%1.C#-"+$/*;%+   :'>BB9 s1F *F3 FF)!r!r"r#r$model_input_namesr valid_kwargsrBILINEARrCONSTANTr%dictr)r9r'rr(rSrrndarrayrr rhFIRSTrrtrrPILImager} __classcell__)rVs@r,rBrBcs/b((*L&*'9'B'B#+/&-*.34 + 4 4!&*1504!&W&W38nt#&W% &W  &W S>D( &W&We &W&WsCx.4'&W%0&W&W&W $&WDK'$.&W 4;&-!&W$ %&WX(:'B'B59;? ) zz) 38n) % ) ++d2 ) !11D8 )  ) \+/34 + 4 459;?-zz-sCx.4'-%0 -  - ++d2 -!11D8-d"&&*.2&*+/"&'+*.:>'+$(-11504/?/E/E;?'EE$;E38nt# E %t+ E t ES>D(E4KE EEsCx.4'E%047E$ETkE $d{E DK'$.!E"4;&-#E$&,%E&!11D8'E* +EN%&"&&*.2&*+/"&'+"*.:>'+$(-1150426(8(>(>;?)ECT*--T*5E0FFEC$;EC38nt# EC %t+ EC t ECS>D(EC4KEC ECt ECsCx.4'EC%047EC$ECTkEC $d{EC DK'$.!EC"4;&-#EC$j(4/%EC&&'EC(!11D8)EC* +EC'ECr+rB)rQN)/r$collections.abcrnumpyrrimage_processing_utilsrrrimage_transformsrr r r r image_utilsr rrrrrrrrrprocessing_utilsrutilsrrrrr get_loggerr!loggerrr(r4rr9r)r1r@rB__all__r*r+r,rs%$UU   -^^   H % l%  DDj!12 D7;--4 38_ &DC*DCN  r+