o iwf@sddlmZddlmZmZddlZddlmZm Z m Z ddl m Z m Z mZddlmZmZmZmZmZmZmZmZmZmZmZmZddlmZmZmZm Z erUddl!Z!e "e#Z$Gd d d eZ%d gZ&dS) )Iterable)OptionalUnionN)BaseImageProcessor BatchFeature get_size_dict)convert_to_rgbresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_flat_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_vision_availableloggingc#seZdZdZdgZdddejdddddddf dedee e e fd e d ed ed e e e fd edee e ee fdee e ee fdeedeeddffdd Zejddfdejde e e e fe fd edee e efdee e efdejf ddZeddddddddddddejdfdedeedee e e fd eed eed ee d eedee e ee fdee e ee fdee e efdeedee e ee e e ffdeededee e efdejjf ddZ   d&dejde e ee e e ffdee e efdee e efdejf d d!Z       d'ded eed ee d eedeee deee dee dee fd"d#Z d(dejde e ee fde e ee fdee e efdejf d$d%ZZ S))JanusImageProcessora Constructs a JANUS 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. min_size (`int`, *optional*, defaults to 14): The minimum allowed size for the resized image. Ensures that neither the height nor width falls below this value after resizing. 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. do_pad (`bool`, *optional*, defaults to `True`): Whether to pad the image to square or not. pixel_valuesTNgp? do_resizesizemin_sizeresample do_rescalerescale_factor do_normalize image_mean image_stddo_convert_rgbdo_padreturnc  stjdi| |dur|nddd}t|dd}||_||_||_||_||_||_|dur2|nt |_ | dur;| nt |_ | |_ | |_||_|durPd|_dStdd|D|_dS) Ni)heightwidthTdefault_to_square)r/r/css|] }t|dVqdS)N)int).0xr4d/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/janus/image_processing_janus.py sz/JanusImageProcessor.__init__..r4)super__init__rrr r"r#r$r%r r&r r'r(r)r!background_colortuple) selfrr r!r"r#r$r%r&r'r(r)kwargs __class__r4r5r8_s"  zJanusImageProcessor.__init__image data_formatinput_data_formatc Ks|durt|}t||\}}t||} t|dd}|d|dkr0td|dd|d|d}|| } tt|| |jtt|| |jg} t|f| |||d|}|S) an Resize an image to dynamically calculated size. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]` or `int`): The size to resize the image to. If a dictionary, it should have the keys `"height"` and `"width"`. 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`: will be inferred from input 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. NTr-r+r,z5Output height and width must be the same. Got height=z and width=)r r"r@rA)rrmaxr ValueErrorr1r!r ) r;r?r r"r@rAr<r+r,max_sizedeltaoutput_size_nonpaddedr4r4r5r s2#  zJanusImageProcessor.resizeimagesreturn_tensorsr9c s|dur|nj}durnj|dur|nj}dur!nj|dur*|nj}dur3njdur<nj| durE| nj} | durN| nj} durWnj dur`nj t dd |}t |}t|sztdt|||d| rdd|D}dd|D}|rt|d rtd durt|d |rfd d|D}| rȇfd d|D}|rՇfd d|D}|rfdd|D}fdd|D}td|i| d}|S)a` 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`): Controls the size of the image 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 image. Only has an effect if `do_resize` is set to `True`. 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 to normalize the image 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 image 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. background_color (`tuple[int, int, int]`): The background color to use for the padding. do_pad (`bool`, *optional*, defaults to `self.do_pad`): Whether to pad the image to square or not. 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-zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)r#r$r%r&r'rr r"cSg|]}t|qSr4)r r2r?r4r4r5 ,z2JanusImageProcessor.preprocess..cSrIr4)rrJr4r4r5rK/rLrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.csg|] }j|dqS))r?r r"rA)r rJ)rAr"r;r r4r5rK<csg|] }j|dqS))r?r9rA) pad_to_squarerJ)r9rAr;r4r5rKCscsg|] }j|dqS))r?scalerA)rescalerJ)rAr$r;r4r5rKMscsg|] }j|dqS)r?meanstdrA) normalizerJ)r&r'rAr;r4r5rKSrMcsg|] }t|dqS)input_channel_dim)r rJ)r@rAr4r5rKXsrdata tensor_type)rr"r#r$r%r&r'r(r)r9r r fetch_imagesrrrCrrlogger warning_oncerr)r;rGrr r"r#r$r%r&r'rHr(r9r)r@rAencoded_outputsr4) r9r@r&r'rAr"r$r;r r5 preprocessstF      zJanusImageProcessor.preprocessrc Cst||\}}|tjkr|jdn|jd}||kr*|dur&t|||}|S|}|St||}t|tr8|g}nt||krFt d|d|tjkrt j |||f|j d} t |D]\} } | | | ddddf<qZ||kr||d} || dd| | |ddf<| S||d} || dddd| | |f<| St j |||f|j d} t |D]\} } | | dddd| f<q||kr||d} || | | |ddddf<| S||d} || dd| | |ddf<| S)a} Pads an image to a square based on the longest edge. Args: image (`np.ndarray`): The image to pad. background_color (`int` or `tuple[int, int, int]`, *optional*, defaults to 0): The color to use for the padding. Can be an integer for single channel or a tuple of integers representing for multi-channel images. If passed as integer in multi-channel mode, it will default to `0` in subsequent channels. data_format (`str` or `ChannelDimension`, *optional*): 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. If unset, will use same as the input image. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for 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. Returns: `np.ndarray`: The padded image. rNz(background_color must have no more than z) elements to match the number of channels)dtype)rrFIRSTshaper rB isinstancer1lenrCnpzerosr` enumerate) r;r?r9r@rAr+r, num_channelsmax_dimresulticolorstartr4r4r5rN`sL           z!JanusImageProcessor.pad_to_squarec CsR|dur|n|j}|durd|jn|}|dur|n|j}|dur#|n|j}|dur,|n|j}t|}t|dtjjrHt |dkrD|S|dS|durRt |d}g} |D]@} t | } |rg|j | |||d} |r{|j | ||d} | ddtj} |r|r|dkrt| tj|d } tj| } | | qVd | i} |dkr|nd}t| |d S) znApplies post-processing to the decoded image tokens by reversing transformations applied during preprocessing.Ng?r)r?r&r'rA)rOrAr0zPIL.Image.ImagerUrrW)r#r$r%r&r'rrdPILImagererr unnormalizerPclipastyperfuint8r rLAST fromarrayappendr) r;rGr#r$r%r&r'rArHrr?rXr4r4r5 postprocesss6     zJanusImageProcessor.postprocesscCsd}t|trt||krtd|dt|n|g|}t|tr7t||kr6td|dt|n|g|}tddt||D}tdd|D}|j||||d}|S) a~ Unnormalizes `image` using the mean and standard deviation specified by `mean` and `std`. image = (image * image_std) + image_mean Args: image (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)` or `(num_channels, image_size, image_size)`): Batch of pixel values to postprocess. image_mean (`float` or `Iterable[float]`): The mean to use for unnormalization. image_std (`float` or `Iterable[float]`): The standard deviation to use for unnormalization. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. rzmean must have z$ elements if it is an iterable, got zstd must have css|] \}}| |VqdSNr4)r2rRrSr4r4r5r6sz2JanusImageProcessor.unnormalize..css|]}d|VqdS)roNr4)r2rSr4r4r5r6srQ)rdrrerCr:ziprT)r;r?r&r'rArirev_image_mean rev_image_stdr4r4r5rrs"      zJanusImageProcessor.unnormalize)rNN)NNNNNNNrz)!__name__ __module__ __qualname____doc__model_input_namesrBICUBICboolrdictstrr1rfloatlistr8rfndarrayrr rrbrrr:rprqr^rNryrrr __classcell__r4r4r=r5r5s4'     ( A       M   8r)'collections.abcrtypingrrnumpyrfimage_processing_utilsrrrimage_transformsr r r image_utilsr r rrrrrrrrrrutilsrrrrrp get_loggerr~r[r__all__r4r4r4r5s 8  Y