sg_JdZddlmZmZmZmZddlZddlm Z ddl m Z ddl m Z mZmZddlmZmZmZmZdd lmZmZmZmZmZmZmZmZmZmZm Z dd l!m"Z"m#Z#e rddl$Z$e#jJe&Z'd eeefd Z(Gd de Z)y)z Image processor class for Vivit.)DictListOptionalUnionN)is_vision_available) TensorType)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizerescaleresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments)filter_out_non_signature_kwargsloggingreturnct|ttfr,t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss c/var/www/html/venv/lib/python3.12/site-packages/transformers/models/vivit/image_processing_vivit.py make_batchedr&5s&4-(Zq D%=-QVdeklmenopeqVr FT5M *~fQi/Hx  z 9&B CCc#eZdZdZdgZddej ddddddddf dedee e fded ed ee e fd ed e e e fd edede e e ee fde e e ee fddffd Zej ddfdej"dee e fdede e e efde e e efdej"f dZ ddej"de e e fd ede e e efde e e eff dZdddddddddddej*df dededee e fded ed ee e fd ed e d edede e e ee fde e e ee fde ede e e efdej"fdZeddddddddddddej*dfdededee e fded ed ee e fd ed e d edede e e ee fde e e ee fde e e efdede e e efdej6j6f dZxZS)VivitImageProcessoraA Constructs a Vivit 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": 256}`): 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 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": 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 `1/127.5`): Defines the scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. offset (`bool`, *optional*, defaults to `True`): Whether to scale the image in both negative and positive directions. Can be overriden by the `offset` 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_valuesTNg? do_resizesizeresampledo_center_crop crop_size do_rescalerescale_factoroffset do_normalize image_mean image_stdrc  @t |d i| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | |_ | | nt|_ | | |_yt|_y) N shortest_edgeFdefault_to_square)heightwidthr/ param_name)super__init__r r+r,r.r/r-r0r1r2r3rr4rr5)selfr+r,r-r.r/r0r1r2r3r4r5kwargs __class__s r%rBzVivitImageProcessor.__init__ms "6"'tos-CTU;!*!6IsUX*DZ&/&;AVr'image data_formatinput_data_formatc t|d}d|vrt||dd|}n/d|vrd|vr |d|df}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 `{"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. Fr9r7)r:rHr<r=zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r,r-rGrH)r r r#keysr)rCrFr,r-rGrHrD output_sizes r%rzVivitImageProcessor.resizes4TU; d "6tO,YjK 'T/>4=9Kcdhdmdmdocpqr r  #/     r'scalec 4t|f|||d|}|r|dz }|S)a Rescale an image by a scale factor. If `offset` is `True`, the image has its values rescaled by `scale` and then offset by 1. If `scale` is 1/127.5, the image is rescaled between [-1, 1]. image = image * scale - 1 If `offset` is `False`, and `scale` is 1/255, the image is rescaled between [0, 1]. image = image * scale Args: image (`np.ndarray`): Image to rescale. scale (`int` or `float`): Scale to apply to the image. offset (`bool`, *optional*): Whether to scale the image in both negative and positive directions. 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 (`ChannelDimension` or `str`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. )rLrGrH)r)rCrFrLr2rGrHrDrescaled_images r%rzVivitImageProcessor.rescales;>!  KK\ `f  +a/Nr'c t||| | | ||||| | r |s tdt|}t|r|rtj d| t |}|r|j||||}|r|j|||}|r|j||| |}| r|j|| | |}t|| |}|S) zPreprocesses a single image.) r0r1r3r4r5r.r/r+r,r-z0For offset, do_rescale must also be set to True.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.)rFr,r-rH)r,rH)rFrLr2rH)rFmeanstdrH)input_channel_dim) rr#rrlogger warning_oncerr center_cropr normalizer)rCrFr+r,r-r.r/r0r1r2r3r4r5rGrHs r%_preprocess_imagez%VivitImageProcessor._preprocess_images& &!)%!)  *OP Pu% 5 !j   s   $ >u E  KKe$]nKoE $$UN_$`E LLuN6evLwE NNZYbsNtE+E;Rcd r'r$return_tensorsc||n |j}||n |j}||n |j}||n |j}||n |j}| | n |j } | | n |j } | | n |j} | | n |j} ||n |j}t|d}||n |j}t|d}t|s tdt|}|Dcgc]/}|Dcgc]!}|j||||||||| | | | ||#c}1}}}d|i}t!|| Scc}wcc}}w) a Preprocess an image or batch of images. Args: videos (`ImageInput`): Video frames to preprocess. Expects a single or batch of video frames with pixel values ranging from 0 to 255. If passing in frames 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 `[-1 - 1]` if `offset` is `True`, `[0, 1]` otherwise. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. offset (`bool`, *optional*, defaults to `self.offset`): Whether to scale the image in both negative and positive directions. 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. Fr9r/r>zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rFr+r,r-r.r/r0r1r2r3r4r5rGrHr*)data tensor_type)r+r-r.r0r1r2r3r4r5r,r r/rr#r&rXr )rCr$r+r,r-r.r/r0r1r2r3r4r5rYrGrHvideoimgr[s r% preprocesszVivitImageProcessor.preprocess!sH"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^!-4;;'3'?|TEVEV #-#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F#:  f%, ) (!# "!&&'%#1')#1!!-)' +&7'   .'>BB/  s1 D>:&D9 D>9D>)TNN)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrstrintrfloatrrrBnpndarrayrrrFIRSTrrXrrPILImager_ __classcell__)rEs@r%r)r)Bst&P((#'9'B'B#$(,5!:>9=WW38nW% W  W S> WWc5j)WWWU5$u+#567WE%e"456W WJ(:'B'B>BDH * zz* 38n* % * eC)9$9:; * $E#/?*?$@A *  * b>BDH &zz&S%Z & & eC)9$9:; & $E#/?*?$@A &V#'+#$( $!:>9=2B2H2HDH<<<38n < % <  <S><<<<<U5$u+#567<E%e"456<./<$E#/?*?$@A< !<|%&#'+#$( $!:>9=;?(8(>(>DH!rCrCrC38n rC % rC  rCS>rCrCrCrCrCU5$u+#567rCE%e"456rC!sJ!78rC&rC $E#/?*?$@A!rC" #rC'rCr'r))*rctypingrrrrnumpyrjtransformers.utilsrtransformers.utils.genericrimage_processing_utilsr r r image_transformsr rrr image_utilsrrrrrrrrrrrutilsrrrm get_loggerr`rTr&r)r@r'r%rys'..21UU    >   H % DDj!12 DRC,RCr'