sgX \dZddlmZmZmZmZmZmZddlZ ddl m Z m Z m Z ddlmZmZmZmZmZddlmZmZmZmZmZmZmZmZmZmZddlm Z m!Z!m"Z"m#Z#e"rddl$Z$e#jJe&Z'd eeefd Z( dd e jRd e*d eee+efd ee*e*ffdZ,Gdde Z-y)zImage processor class for TVP.)DictIterableListOptionalTupleUnionN)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_availableloggingreturnct|ttfr,t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss _/var/www/html/venv/lib/python3.12/site-packages/transformers/models/tvp/image_processing_tvp.py make_batchedr(4s&4-(Zq D%=-QVdeklmenopeqVr FT5M *~fQi/Hx  z 9&B CC input_imagemax_sizeinput_data_formatct||\}}||k\r|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_sizer5Asm #;0ABMFE  f$ &  u$ &  OS^ ,D Kr)c+eZdZdZdgZddej dddddddejddddfde de e e fd ed e d e e e fd e d e e efde de e e fde eeefdede de dee eeefdee eeefddf fd Zej ddfdej(de e e fd edee e efdee e efdej(f dZddejddfdej(de e e fde eeefdedee e efdee e eff dZdddddddddddddddej0dfdede de e e fd ed e d e e e fd e d ede de e e fde eeefdede de dee eeefdee eeefdeedee e efdej(f&dZeddddddddddddddddej0dfde eeeeeefde de e e fd ed e d e e e fd e d ede de e e fde eeefdede de dee eeefdee eeefdee e efdedee e efdej<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 overriden 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_resizer4resampledo_center_crop crop_size do_rescalerescale_factordo_padpad_sizeconstant_valuespad_mode do_normalizedo_flip_channel_order image_mean image_stdr c Vt|di|||nddi}||nddd}| | nddd} ||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||nt|_|||_yt"|_y)N longest_edge)r/r0)super__init__r9r4r;r<r:r=r>r?r@rArBrCrDrrErrF)selfr9r4r:r;r<r=r>r?r@rArBrCrDrErFkwargs __class__s r'rLzTvpImageProcessor.__init__s& "6"'tnc-B!*!6IsUX*DZ&/&;AVr)image data_formatr,c 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/r0rHzCSize must have 'height' and 'width' or 'longest_edge' as keys. Got )r4r:rQr,)r r5r%keysr)rMrPr4r:rQr,rN output_sizes r'rzTvpImageProcessor.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/r0rz0The padding size must be greater than image size)moderArQr,)rgetr%r)rMrPr@rArBrQr,rNr/r0 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.) r=r>rCrErFr?size_divisibilityr;r<r9r4r:)rPr4r:r,)r4r,)rPscaler,)rPmeanstdr,)rPr@rArBr,)rPr,)input_channel_dim) rrr center_croprescale normalizeastypenpfloat32rarr)rMrPr9r4r:r;r<r=r>r?r@rArBrCrDrErFrQr,rNs r'_preprocess_imagez#TvpImageProcessor._preprocess_image s0 &!)%!&) u% KKe$]nKoE $$UN_$`E LLuNVgLhE NNll2::.ZYbs#E NN! /!"3 #E !&UFWXE+E;Rcd r)r&return_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) 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. FrSr<) param_namezkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rPr9r4r:r;r<r=r>r?r@rArBrCrDrErFrQr,r8)data tensor_type)r9r:r;r=r>r?r@rArBrCrDrErFr4r r<rr%r(rlarrayrnr )rMr&r9r4r:r;r<r=r>r?r@rArBrCrDrErFrorQr,videoimgrrs r' preprocesszTvpImageProcessor.preprocessSs`"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^!-4;;'38-<-H/dNbNb'8T]]'3'?|TEVEV %:%F !DLfLf $.#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F#:  f%8 5 43 HH, %+*)**!"+!!)'5"+#-'5%!)(7!)%1.C#-"+$/*;%+   :'>BB9 s1F *F3 FF)!__name__ __module__ __qualname____doc__model_input_namesrBILINEARr CONSTANTboolrstrr.rfloatrrrrLrlndarrayrrraFIRSTrrnrrPILImagerw __classcell__)rOs@r'r7r7Ts/b((#'9'B'B#$(,3#'9: + 4 4!&*:>9=!&W&W38n&W% &W  &W S> &W&Wc5j)&W&WsCx.&Wuhuo56&W&W&W $&WU5$u+#567&W E%e"456!&W$ %&WX(:'B'B>BDH ) zz) 38n) % ) eC)9$9:; ) $E#/?*?$@A )  ) \$(9: + 4 4>BDH-zz-sCx.-uhuo56 -  - eC)9$9:; -$E#/?*?$@A-d#'+#$( $#'9= $!&*:>9=2B2H2HDH'GGG38n G % G  GS>GGGGsCx.Guhuo56GGG $G U5$u+#567!G"E%e"456#G$./%G&$E#/?*?$@A'G* +GR%&#'+#$( $#'9= $!&*:>9=;?(8(>(>DH)JCj$z"2Dj9I4JJKJCJC38n JC % JC  JCS>JCJCJCJCsCx.JCuhuo56JCJCJC $JC U5$u+#567!JC"E%e"456#JC$!sJ!78%JC&&'JC($E#/?*?$@A)JC* +JC'JCr)r7)rIN).r{typingrrrrrrnumpyrlimage_processing_utilsr r r image_transformsr rrrr image_utilsrrrrrrrrrrutilsrrrrr get_loggerrxloggerr(rr.rr5r7rJr)r'rs%??UU   _^   H % DDj!12 D@D c+;&; <= 38_ &JC*JCr)