o Zh9K@sdZddlmZmZmZmZddlZddlm Z ddl m Z ddl m Z mZmZddlmZmZmZmZdd lmZmZmZmZmZmZmZmZmZmZm Z dd l!m"Z"m#Z#e r]ddl$Z$e#%e&Z'd eeefd d Z(Gddde Z)dgZ*dS)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_kwargsloggingreturncCsrt|ttfrt|dttfrt|ddr|St|ttfr*t|dr*|gSt|r2|ggStd|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videosr#_/var/www/auris/lib/python3.10/site-packages/transformers/models/vivit/image_processing_vivit.py make_batched5s0r%c#seZdZdZdgZddejddddddddf dedee e e fded ed ee e e fd ed e e e fd ededee e ee fdee e ee fddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZ   d"dejde e e fd edee e efdee e eff ddZdddddddddddejdf dedeedee e e fded eed ee e e fd eed ee d eedeedee e ee fdee e ee fdeedee e efdejfddZeddddddddddddejdfdedeedee e e fded eed ee e e fd eed ee d eedeedee e ee fdee e ee fdee e efdedee e efdejjf d d!ZZS)#VivitImageProcessoraC 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 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 `1/127.5`): 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 overridden 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  stjd i| |dur|nddi}t|dd}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ | |_ | durK| nt |_ | durW| |_dSt|_dS) N shortest_edgeFdefault_to_square)heightwidthr, param_namer#)super__init__r r(r)r+r,r*r-r.r/r0rr1rr2) selfr(r)r*r+r,r-r.r/r0r1r2kwargs __class__r#r$r=ms   zVivitImageProcessor.__init__image data_formatinput_data_formatcKsxt|dd}d|vrt||dd|d}nd|vr&d|vr&|d|df}n td|t|f||||d|S) a Resize an image. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Size of the output image. If `size` is of the form `{"height": h, "width": w}`, the output image will have the size `(h, w)`. If `size` is of the form `{"shortest_edge": s}`, the output image will have its shortest edge of length `s` while keeping the aspect ratio of the original image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`): Resampling filter to use when resiizing the image. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the image. If not provided, it will be the same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. Fr5r3)r6rDr8r9zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r)r*rCrD)r r r!keysr)r>rBr)r*rCrDr?Z output_sizer#r#r$rs$  zVivitImageProcessor.resizescalecKs(t|f|||d|}|r|d}|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. )rFrCrD)r )r>rBrFr/rCrDr?Zrescaled_imager#r#r$r szVivitImageProcessor.rescalec Cst||| | | |||||d | r|stdt|}|r%t|r%td|dur-t|}|r8|j||||d}|rB|j|||d}|rM|j ||| |d}| rX|j || | |d}t || |d }|S) zPreprocesses a single image.) r-r.r0r1r2r+r,r(r)r*z0For offset, do_rescale must also be set to True.zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.N)rBr)r*rD)r)rD)rBrFr/rD)rBmeanZstdrD)Zinput_channel_dim) rr!rrloggerZ warning_oncerrZ center_cropr normalizer)r>rBr(r)r*r+r,r-r.r/r0r1r2rCrDr#r#r$_preprocess_images>  z%VivitImageProcessor._preprocess_imager"return_tensorscs6durn j dur n j durn jdur!n j dur* n j dur3 n j dur<n jdurEn jdurNn j durW n j t dd durfn j t ddt |swt dt|} fdd|D}d |i}t|| d S) 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. NFr5r,r:zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.cs8g|]} fdd|DqS)cs2g|]} j|  dqS))rBr(r)r*r+r,r-r.r/r0r1r2rCrD)rK).0Zimgr,rCr+r0r-r(r1r2rDr/r*r.r>r)r#r$ }s&z=VivitImageProcessor.preprocess...r#)rMZvideorNr#r$rO|s $z2VivitImageProcessor.preprocess..r')dataZ tensor_type)r(r*r+r-r.r/r0r1r2r)r r,rr!r%r )r>r"r(r)r*r+r,r-r.r/r0r1r2rLrCrDrPr#rNr$ preprocess!s.D  $ zVivitImageProcessor.preprocess)TNN)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBILINEARboolrrstrintrfloatrr=npZndarrayrrr ZFIRSTrrKrrPILZImagerQ __classcell__r#r#r@r$r&BsB(     %  1  +      >     r&)+rUtypingrrrrnumpyrZZtransformers.utilsrZtransformers.utils.genericrZimage_processing_utilsr r r Zimage_transformsr r rrZ image_utilsrrrrrrrrrrrutilsrrr[Z get_loggerrRrIr%r&__all__r#r#r#r$s"  4    W