o iA@sdZddlmZmZddlZddlmZmZm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZmZdd lm Z erUddl!Z!e"e#Z$d e%e%efd d Z&e d dGdddeZ'dgZ(dS)z#Image processor class for VideoMAE.)OptionalUnionN)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!j/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/videomae/image_processing_videomae.py make_batched3s0r#)vision)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 fdeed eed ee e e fd eed ee d eedee e ee fdee e ee fdeedee e efdejfddZedddddddddddejdf dedeedee e e fdeed 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__rr(r)r+r,r*r-r.r/r r0r r1) selfr(r)r*r+r,r-r.r/r0r1kwargs __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. Fr4r2)r5rBr6r7zDSize must have 'height' and 'width' or 'shortest_edge' as keys. Got )r)r*rArB)rrrkeysr )r<r@r)r*rArBr= 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.r/r0r1r+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)r@r)r*rB)r)rB)r@scalerB)r@meanstdrB)input_channel_dim) rrrlogger warning_oncerr center_croprescale normalizer )r<r@r(r)r*r+r,r-r.r/r0r1rArBr!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. NFr4r,r8zkInvalid 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)) r@r(r)r*r+r,r-r.r/r0r1rArB)rN).0img r,rAr+r/r-r(r0r1rBr*r.r<r)r!r" Es$z@VideoMAEImageProcessor.preprocess...r!)rPvideorRr!r"rSDs "z5VideoMAEImageProcessor.preprocess..r')data tensor_type)r(r*r+r-r.r/r0r1r)rr,rrr#r)r<r r(r)r*r+r,r-r.r/r0r1rOrArBrUr!rRr" preprocesss,A  " z!VideoMAEImageProcessor.preprocess)__name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrintrfloatrr;npndarrayr r FIRSTrrNrrPILImagerW __classcell__r!r!r>r"r&@s%     #  /      9     r&))r[typingrrnumpyrcimage_processing_utilsrrrimage_transformsrr r image_utilsr r r rrrrrrrrutilsrrrrutils.import_utilsrrf get_loggerrXrIrr#r&__all__r!r!r!r"s"4