T^(h@dZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZm Z e jBe"Z#Gd d e Z$y) z{ Image processor class for InstructBLIPVideo. Largely copy of Blip2Processor with addition of a video processing abilities )DictListOptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResampling VideoInputinfer_channel_dimension_formatis_scaled_imagemake_batched_videosto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsloggingc.eZdZdZdgZddej ddddddf dedee e fded ed e e e fd ed e e e ee fd e e e ee fdeddffd Zej ddfdej"dee e fdede e e efde e e efdej"f dZedddddddddddej*df dede ede ee e fded e ed e e d e ed e e e ee fd e e e ee fde e e efde edede e e efdefdZddddddddddej*df dede ede ee e fded e ed e e d e ed e e e ee fd e e e ee fde edede e e efdej"fdZxZS)InstructBlipVideoImageProcessora Constructs a InstructBLIPVideo 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`, *optional*, defaults to `{"height": 384, "width": 384}`): Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BICUBIC`): Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` 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`): Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. 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. 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. 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. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `True`): Whether to convert the image to RGB. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbreturnc  t |di| ||nddd}t|d}||_||_||_||_||_||_||nt|_ ||nt|_ | |_ y)Ni)heightwidthTdefault_to_square)super__init__r r r!r"r#r$r%rr&rr'r() selfr r!r"r#r$r%r&r'r(kwargs __class__s /var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/instructblipvideo/image_processing_instructblipvideo.pyr1z(InstructBlipVideoImageProcessor.__init__Ts "6"'tc-JTT:"   $,((2(>*DT&/&;,image data_formatinput_data_formatc t|}d|vsd|vrtd|j|d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. r+r,zFThe `size` dictionary must contain the keys `height` and `width`. Got )r!r"r8r9)r ValueErrorkeysr )r2r7r!r"r8r9r3 output_sizes r5r z&InstructBlipVideoImageProcessor.resizepsyFT" 4 7$#6efjfofofqerst tH~tG}5   #/     r6imagesreturn_tensorscP||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }| | n |j } | | n |j} ||n |j}t|d}t|}t||||| |||t|s td|Dcgc]-}|Dcgc]}|j||||||||| | | |  !c}/}}}td|i| }|Scc}wcc}}w)a Preprocess a video or batch of images/videos. Args: videos (`VideoInput`): Video frames to preprocess. Expects a single or batch of videos as a list of frames with pixel values ranging from 0 to 255. If passing in video with pixel values between 0 and 1, set `do_rescale=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the video. size (`Dict[str, int]`, *optional*, defaults to `self.size`): Controls the size of the video after `resize`. The shortest edge of the image is resized to `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest edge equal to `int(size["shortest_edge"] * (1333 / 800))`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the video. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the video values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the video by if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether to normalize the video. image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`): Image mean to normalize the video by if `do_normalize` is set to `True`. image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`): Image standard deviation to normalize the video by if `do_normalize` is set to `True`. do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`): Whether to convert the image to RGB. 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: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the 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. Fr-)r#r$r%r&r'r r!r"zkInvalid input type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) r7r r!r"r#r$r%r&r'r(r8r9r)data tensor_type)r r"r#r$r%r&r'r(r!r rrrr;_preprocess_imager )r2r>r r!r"r#r$r%r&r'r?r(r8r9videosvideoframerencoded_outputss r5 preprocessz*InstructBlipVideoImageProcessor.preprocesss{@"+!6IDNN '38#-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN +9+E4K^K^'tTYYTU;$V,%!)%! F#: . % $# &&'%)#1!-)'#1 +&7'    *'^\,JXfg+  s D" $D D"D"c 8| r t|}t|}|r t|rtj d| t |} |r|j |||| }|r|j||| }|r|j||| | }t|| | }|S)NzIt looks like you are trying to rescale already rescaled video frames. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r7r!r"r9)r7scaler9)r7meanstdr9)input_channel_dim) r rrlogger warning_oncerr rescale normalizer ) r2r7r r!r"r#r$r%r&r'r(r8r9s r5rCz1InstructBlipVideoImageProcessor._preprocess_images "5)Eu% /%0   s   $ >u E  KKe$]nKoE LLuNVgLhE NNZYbsNtE+E;Rcd r6)__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrstrintrfloatrrr1npndarrayrr rFIRSTrrr rHrrC __classcell__)r4s@r5rr/s D((#'9'A'A,3!:>9=#--38n-% -  - c5j) --U5$u+#567-E%e"456-- -@(:'A'A>BDH / zz/ 38n/ % / eC)9$9:; / $E#/?*?$@A /  / d%&"$()-'+%)*.'+:>9=;?)-(8(>(>DHttD>ttCH~& t % t TN t!ttntU5$u+#567tE%e"456t!sJ!78t!t&t$E#/?*?$@At t'tr!$()-'+%)*.'+:>9=)-(8(>(>DH++D>+tCH~& + % + TN +!+tn+U5$u+#567+E%e"456+!+&+$E#/?*?$@A+ +r6r)%rUtypingrrrrnumpyr\image_processing_utilsrr r image_transformsr r r image_utilsrrrrrrrrrrrrutilsrrr get_loggerrRrNrr/r6r5rgsa /.UUSS    JI   H %V&8Vr6