U 4AfT@sdZddlmZmZmZmZmZddlmZddl m Z m Z ddl m Z mZddlmZmZmZmZmZmZddlmZmZd d d gZd d dgZddZGddde ZdS)z"Image processor class for Idefics.)CallableDictListOptionalUnion)Image)BaseImageProcessor BatchFeature)resizeto_channel_dimension_format)ChannelDimension ImageInputPILImageResamplingmake_list_of_imagesto_numpy_array valid_images) TensorTypeis_torch_availableg3<4'?gwg M?gy{ ?gB91?gwt.?g U?cCsB|jdkr|S|d}td|jd}t||}|d}|S)NZRGBZRGBA)rr)modeconvertrnewsizealpha_composite)imageZ image_rgbaZ backgroundrrX/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/idefics/image_processing_idefics.pyconvert_to_rgb&s    rc seZdZdZdgZd eeeee efeeee efeeddfdd Z ddddde j fe eeeeeefeeee efeeee efeeeee fe d d d ZZS) IdeficsImageProcessora1 Constructs a Idefics image processor. Args: image_size (`int`, *optional*, defaults to 224): Resize to image size image_mean (`float` or `List[float]`, *optional*, defaults to `IDEFICS_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 `IDEFICS_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. image_num_channels (`int`, *optional*, defaults to 3): Number of image channels. pixel_valuesNr) image_size image_mean image_stdimage_num_channelsreturnc s*tjf|||_||_||_||_dS)N)super__init__r"r%r#r$)selfr"r#r$r%kwargs __class__rrr(Hs zIdeficsImageProcessor.__init__)imagesr%r"r#r$ transformreturn_tensorsr&c  s8|dk r |nj}|dk r|nj}dk r0njdk rBnj||ft|trjt|dkrjgSt|}t|st ddk rt st dddl } fdd|D}| |Sdd|D}dd|D}fd d|D}fd d|D}fd d|D}d d|D}td |i|dd }|S)a Preprocess a batch of images. Args: images (`ImageInput`): A list of images to preprocess. image_size (`int`, *optional*, defaults to `self.image_size`): Resize to image size image_num_channels (`int`, *optional*, defaults to `self.image_num_channels`): Number of image channels. image_mean (`float` or `List[float]`, *optional*, defaults to `IDEFICS_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 `IDEFICS_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. transform (`Callable`, *optional*, defaults to `None`): A custom transform function that accepts a single image can be passed for training. For example, `torchvision.Compose` can be used to compose multiple transforms. If `None` - an inference mode is assumed - and then a preset of inference-specific transforms will be applied to the images Returns: a PyTorch tensor of the processed images NrzkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.z.To pass in `transform` torch must be installedcsg|] }|qSrr.0x)r.rr sz4IdeficsImageProcessor.preprocess..cSsg|] }t|qSr)rr0rrrr3scSsg|] }t|qSr)rr0rrrr3scsg|]}t|tjdqS))Zresample)r rZBICUBICr0)rrrr3scsg|]}j|ddqS)gp?)rZscale)Zrescale)r1r)r)rrr3scsg|]}j|dqS))ZmeanZstd) normalizer0)r#r$r)rrr3scSsg|]}t|tjqSr)r r ZFIRSTr0rrrr3sr )dataZ tensor_type)r"r%r#r$ isinstancelistlenrr ValueErrorr ImportErrortorchstackr ) r)r-r%r"r#r$r.r/r*r;r)r#r$r)rr.r preprocessWs4&  z IdeficsImageProcessor.preprocess)r!NNr)__name__ __module__ __qualname____doc__Zmodel_input_namesintrrfloatrr(rZPYTORCHrrstrrr= __classcell__rrr+rr3s:rN)rAtypingrrrrrZPILrZimage_processing_utilsr r Zimage_transformsr r Z image_utilsr rrrrrutilsrrZIDEFICS_STANDARD_MEANZIDEFICS_STANDARD_STDrrrrrrs