o ZhA@sdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZm Z dd l!m"Z"erYddl#Z#e $e%Z&d eeefd d Z'e"d dGddde Z(dgZ)dS)z#Image processor class for VideoMAE.)DictListOptionalUnionN)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)requiresreturncCsrt|ttfrt|dttfrt|ddr|St|ttfr*t|dr*|gSt|r2|ggStd|)Nrz"Could not make batched video from ) isinstancelisttupler ValueError)videosr#e/var/www/auris/lib/python3.10/site-packages/transformers/models/videomae/image_processing_videomae.py make_batched3s0r%)Zvision)backendsc!seZdZdZdgZddejdddddddf dedee e e fded ed ee e e fd ed e e e fd edee e ee fdee e ee fddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZddddddddddejdf dedeedee e e fded eed ee e e fd eed ee d eedee e ee fdee e ee fdeedee e efdejfddZedddddddddddejdf dedeedee e e fded eed ee e e fd eed ee d eedee e ee fdee e ee fdee e efdedee e efdejjfddZZS)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  stjdi| |dur|nddi}t|dd}|dur|nddd}t|dd}||_||_||_||_||_||_||_ ||_ | durH| nt |_ | durT| |_dSt |_dS) N shortest_edgeFdefault_to_square)heightwidthr- param_namer#)super__init__r r)r*r,r-r+r.r/r0r r1rr2) selfr)r*r+r,r-r.r/r0r1r2kwargs __class__r#r$r<is  zVideoMAEImageProcessor.__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)r6rCr7r8zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r*r+rBrC)r r r!keysr )r=rAr*r+rBrCr>Z output_sizer#r#r$r s$  zVideoMAEImageProcessor.resizec Cst||| | | |||||d t|}|rt|rtd| dur%t|} |r0|j|||| d}|r:|j||| d}|rD|j||| d}| rO|j || | | d}t || | d}|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.N)rAr*r+rC)r*rC)rAscalerC)rAmeanZstdrC)Zinput_channel_dim) rrrloggerZ warning_oncerr Z center_cropZrescale normalizer )r=rAr)r*r+r,r-r.r/r0r1r2rBrCr#r#r$_preprocess_images: z(VideoMAEImageProcessor._preprocess_imager"return_tensorsc s"durn j dur n j durn jdur!n j dur* n j dur3n jdur<n jdurEn j durN n j t dd dur]n j t ddt |snt dt |} f dd|D}d |i}t|| d S) aH 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.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-r9zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.cs6g|]} f dd|DqS)cs0g|]} j|  d qS)) rAr)r*r+r,r-r.r/r0r1r2rBrC)rI).0Zimg r-rBr,r0r.r)r1r2rCr+r/r=r*r#r$ Es$z@VideoMAEImageProcessor.preprocess...r#)rKZvideorLr#r$rMDs "z5VideoMAEImageProcessor.preprocess..r()dataZ tensor_type)r)r+r,r.r/r0r1r2r*r r-rr!r%r)r=r"r)r*r+r,r-r.r/r0r1r2rJrBrCrNr#rLr$ preprocesss,A  " z!VideoMAEImageProcessor.preprocess)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBILINEARboolrrstrintrfloatrr<npZndarrayrr ZFIRSTrrIrrPILZImagerO __classcell__r#r#r?r$r'@s%     #  /      9     r')*rStypingrrrrnumpyrXZimage_processing_utilsrrr Zimage_transformsr r r Z image_utilsr rrrrrrrrrrutilsrrrrZutils.import_utilsrrYZ get_loggerrPrGr%r'__all__r#r#r#r$s"4