o ZhB@sdZddlmZmZmZmZddlZddlm Z m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd lm Z m!Z!e"e#Z$Gd d d e Z%d gZ&dS) 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 ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargslogging) VideoInputmake_batched_videoscsPeZdZdZdgZddejddddddf dedee e e fded ed e e e fd ed ee e ee fd ee e ee fdeddffdd Zejddfdejde e e fdedee e efdee e efdejf ddZedddddddddddejdf dedeedee e e fded eed ee d eed ee e ee fd ee e ee fdee e efdeededee e efdefddZddddddddddejdf dedeedee e e fded eed ee d eed ee e ee fd ee e ee fdeededee e efdejfddZZS)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  stjdi| |dur|nddd}t|dd}||_||_||_||_||_||_|dur2|nt |_ |dur;|nt |_ | |_ dS)Ni)heightwidthTZdefault_to_square)super__init__r rrr r!r"r#r r$rr%r&) selfrrr r!r"r#r$r%r&kwargs __class__r+w/var/www/auris/lib/python3.10/site-packages/transformers/models/instructblipvideo/image_processing_instructblipvideo.pyr-Ts   z(InstructBlipVideoImageProcessor.__init__image data_formatinput_data_formatcKsTt|}d|vs d|vrtd||d|df}t|f||||d|S)a Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Returns: `np.ndarray`: The resized image. r(r)zFThe `size` dictionary must contain the keys `height` and `width`. Got )rr r4r5)r ValueErrorkeysr )r.r3rr r4r5r/Z output_sizer+r+r2r ps#z&InstructBlipVideoImageProcessor.resizeimagesreturn_tensorsc s$durn jdurn jdurn j dur! n j dur*n jdur3n jdur<n jdurEn j durN n j t dd t |}t dt   dt|sttd f dd|D}td |i| d }|S) 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. NFr*z`InstructBlipVideoImageProcessor` is deprecated and will be removed in v5.0. We recommend to load an instance of `InstructBlipVideoVideoProcessor` to process videos for the model. )r!r"r#r$r%rrr zkInvalid input type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.cs4g|]} f dd|DqS)cs.g|]} j|  d qS)) r3rrr r!r"r#r$r%r&r4r5)_preprocess_image).0frame r4r&r#r!rr$r%r5r r"r.rr+r2 s"zIInstructBlipVideoImageProcessor.preprocess...r+)r;Zvideor=r+r2r>s  z>InstructBlipVideoImageProcessor.preprocess..r)dataZ tensor_type)rr r!r"r#r$r%r&rr rloggerwarningrrr6r)r.r8rrr r!r"r#r$r%r9r&r4r5ZvideosrZencoded_outputsr+r=r2 preprocesssB@   z*InstructBlipVideoImageProcessor.preprocessc Cs| rt|}t|}|rt|rtd| durt|} |r(|j|||| d}|r2|j||| d}|r=|j||| | d}t || | d}|S)NzIt looks like you are trying to rescale already rescaled video frames. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r3rr r5)r3scaler5)r3meanZstdr5)Zinput_channel_dim) r rrr@Z warning_oncerr Zrescale normalizer ) r.r3rrr r!r"r#r$r%r&r4r5r+r+r2r:s" z1InstructBlipVideoImageProcessor._preprocess_image)__name__ __module__ __qualname____doc__Zmodel_input_namesrZBICUBICboolrrstrintrfloatrr-npZndarrayrr rZFIRSTrrrrBrr: __classcell__r+r+r0r2r/s"       2      }     r)'rItypingrrrrnumpyrNZimage_processing_utilsrrr Zimage_transformsr r r Z image_utilsr rrrrrrrrrutilsrrrZ video_utilsrrZ get_loggerrFr@r__all__r+r+r+r2s0