qi?dZddlZddlmZmZmZddlmZm Z m Z ddl m Z m Z mZmZmZmZmZmZmZmZmZddlmZmZmZmZddlmZerddlZej>e Z!d e"e"efd Z#ed Gd deZ$dgZ%y)z#Image processor class for VideoMAE.N)BaseImageProcessor BatchFeature get_size_dict)get_resize_output_image_sizeresizeto_channel_dimension_format) IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availablelogging)requiresreturnct|ttfr,t|dttfrt|ddr|St|ttfrt|dr|gSt|r|ggSt d|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videoss h/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/videomae/image_processing_videomae.py make_batchedr"0s&4-(Zq D%=-QVdeklmenopeqVr FT5M *~fQi/Hx  z 9&B CC)vision)backendsc |eZdZdZdgZddej dddddddf dedee e fdzded ed ee e fdzd ed e e zd ede e e zdzde e e zdzddffd Z ej ddfdejdee e fdede ezdzde ezdzdejf dZddddddddddej$df dededzdee e fdzdedzd edzd ee e fdzd edzd e dzd edzde e e zdzde e e zdzdedzde ezdzdejfdZedddddddddddej$df dededzdee e fdzdedzd edzd ee e fdzd edzd e dzd edzde e e zdzde e e zdzde ezdzdede ezdzdej0j0fdZxZS)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  2t |di| ||nddi}t|d}||nddd}t|d}||_||_||_||_||_||_||_ ||_ | | nt|_ | | |_yt|_y) N shortest_edgeFdefault_to_square)heightwidthr- param_name)super__init__rr)r*r,r-r+r.r/r0r r1r r2) selfr)r*r+r,r-r.r/r0r1r2kwargs __class__s r!r>zVideoMAEImageProcessor.__init__fs "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. Fr6r4)r7rDr8r9zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r*r+rCrD)rrrkeysr)r?rBr*r+rCrDr@ output_sizes r!rzVideoMAEImageProcessor.resizes4TU; d "6tO,YjK 'T/>4=9Kcdhdmdmdocpqr r  #/     r#c tt||| | | ||||| t|}|r t|rtj d| t |} |r|j |||| }|r|j||| }|r|j||| }| r|j|| | | }t|| | }|S)zPreprocesses a single image.) r.r/r0r1r2r,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.)rBr*r+rD)r*rD)rBscalerD)rBmeanstdrD)input_channel_dim) rrrlogger warning_oncerr center_croprescale normalizer )r?rBr)r*r+r,r-r.r/r0r1r2rCrDs r!_preprocess_imagez(VideoMAEImageProcessor._preprocess_images" &!)%!) u% /%0   s   $ >u E  KKe$]nKoE $$UN_$`E LLuNVgLhE NNZYbsNtE+E;Rcd r#r return_tensorscf||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}0}}}d|i}t|| Scc}wcc}}w) a 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.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. Fr6r-r:zSInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, or torch.Tensor) rBr)r*r+r,r-r.r/r0r1r2rCrDr()data tensor_type)r)r+r,r.r/r0r1r2r*rr-rrr"rRr)r?r r)r*r+r,r-r.r/r0r1r2rSrCrDvideoimgrUs r! preprocessz!VideoMAEImageProcessor.preprocesssq~"+!6IDNN '38+9+E4K^K^#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN 'tTYYTU;!*!6IDNN !) D F#rs sf%* ' &!!  &&'%#1')#1!-)' +&7'   ,'>BB-  s! D-*%D( D-(D-)__name__ __module__ __qualname____doc__model_input_namesrBILINEARbooldictstrintfloatrr>npndarrayr rFIRSTr rRrrPILImagerY __classcell__)rAs@r!r'r'=s#J((&*'9'B'B#+/&-!1504WW38nt#W% W  W S>D( WWe WWDK'$.W4;&-W WF(:'B'B59;? * zz* 38n* % * ++d2 * !11D8 *  * ^"&&*.2&*+/"&'+$(1504/?/E/E;?77$;738nt# 7 %t+ 7 t 7S>D(74K7 7Tk7DK'$.74;&-7&,7!11D87 7r%&"&&*.2&*+/"&'+$(150426(8(>(>;?hChC$;hC38nt# hC %t+ hC t hCS>D(hC4KhC hCTkhCDK'$.hC4;&-hCj(4/hC&hC!11D8hC !hC'hCr#r')&r]numpyreimage_processing_utilsrrrimage_transformsrrr image_utilsr r r r rrrrrrrutilsrrrrutils.import_utilsrrh get_loggerrZrMrr"r'__all__r<r#r!rss*UU    _^*   H % DDj!12 D ;UC/UC UCp $ $r#