a  d]@sPddlZddlmZmZmZmZmZmZddlZ ddl Z ddl m Z ddl mZmZmZmZmZmZmZmZddlmZmZmZmZmZmZerddlZddlZe e ej!j"e dkrej#j$Z%nej#Z%ererddl&Z&ede j'd edee j'ed fZ(Gd d d eZ)d d Z*ddZ+ddZ,ddZ-d1e.ee(dddZ/e j'dddZ0e j'e)dddZ1e j'e.dddZ2d2e j'e)ee.e.fd d!d"Z3ee4eeeffe5d#d$d%Z6ee4eeeffe5d#d&d'Z7eee4eeeffe5d(d)d*Z8eee4eeeffe5d(d+d,Z9ee4dfddd-d.Z:Gd/d0d0Z;dS)3N) TYPE_CHECKINGDictIterableListTupleUnion)version) ExplicitEnum is_jax_tensor is_tf_tensoris_torch_availableis_torch_tensoris_vision_availablerequires_backendsto_numpy)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDIMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDOPENAI_CLIP_MEANOPENAI_CLIP_STDz9.1.0zPIL.Image.Imagez torch.Tensorc@seZdZdZdZdS)ChannelDimensionZchannels_firstZ channels_lastN)__name__ __module__ __qualname__FIRSTLASTrra/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/image_utils.pyr>srcCstot|tjjSN)r isinstancePILImageimgrrr is_pil_imageCsr&cCs8trt|tjjp6t|tjp6t|p6t|p6t|Sr ) rr!r"r#npndarrayrr r r$rrris_valid_imageGs r)cCs8t|ttfr(|D]}t|sdSqn t|s4dSdS)NFT)r!listtuple valid_imagesr))Zimgsr%rrrr,Qs r,cCst|ttfrt|dSdS)NrF)r!r*r+r)r$rrr is_batched]s r-)expected_ndimsreturncCst|r |St|tjjr |gSt|rx|j|dkr@t|}n4|j|krR|g}n"td|dd|d|jd|Stdt|ddS) a Ensure that the input is a list of images. If the input is a single image, it is converted to a list of length 1. If the input is a batch of images, it is converted to a list of images. Args: images (`ImageInput`): Image of images to turn into a list of images. expected_ndims (`int`, *optional*, defaults to 3): Expected number of dimensions for a single input image. If the input image has a different number of dimensions, an error is raised. r z%Invalid image shape. Expected either z or z dimensions, but got z dimensions.ztInvalid image type. Expected either PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray, but got .N) r-r!r"r#r)ndimr* ValueErrortype)Zimagesr/rrrmake_list_of_imagescs(   r5)r0cCs@t|stdt|tr8t|tjjr8t|St |S)NzInvalid image type: ) r)r3r4rr!r"r#r'arrayrr$rrrto_numpy_arrays  r7)imager0cCsl|jdkrd\}}n$|jdkr(d\}}ntd|j|j|dvrLtjS|j|dvr`tjStddS)z Infers the channel dimension format of `image`. Args: image (`np.ndarray`): The image to infer the channel dimension of. Returns: The channel dimension of the image. r.)rr r.z(Unsupported number of image dimensions: z(Unable to infer channel dimension formatN)r2r3shaperrr)r8Z first_dimZlast_dimrrrinfer_channel_dimension_formats    r=cCsBt|}|tjkr|jdS|tjkr0|jdStd|dS)z Returns the channel dimension axis of the image. Args: image (`np.ndarray`): The image to get the channel dimension axis of. Returns: The channel dimension axis of the image. r.r Unsupported data format: N)r=rrr2rr3r8 channel_dimrrrget_channel_dimension_axiss     rA)r8r@r0cCs^|durt|}|tjkr.|jd|jdfS|tjkrL|jd|jdfStd|dS)a Returns the (height, width) dimensions of the image. Args: image (`np.ndarray`): The image to get the dimensions of. channel_dim (`ChannelDimension`, *optional*): Which dimension the channel dimension is in. If `None`, will infer the channel dimension from the image. Returns: A tuple of the image's height and width. Nr>)r=rrr<rr3r?rrrget_image_sizes   rE) annotationr0cCsVt|trRd|vrRd|vrRt|dttfrRt|ddksNt|ddtrRdSdS)Nimage_id annotationsrTFr!dictr*r+lenrFrrr"is_valid_annotation_coco_detections rMcCs^t|trZd|vrZd|vrZd|vrZt|dttfrZt|ddksVt|ddtrZdSdS)NrGZ segments_info file_namerTFrIrLrrr!is_valid_annotation_coco_panoptics   rO)rHr0cCstdd|DS)Ncss|]}t|VqdSr )rM.0annrrr z3valid_coco_detection_annotations..allrHrrr valid_coco_detection_annotationssrXcCstdd|DS)Ncss|]}t|VqdSr )rOrPrrrrSrTz2valid_coco_panoptic_annotations..rUrWrrrvalid_coco_panoptic_annotationssrYcCsttdgt|trp|ds*|drDtjtj |ddj }qt j |r^tj|}qtd|dnt|tjjr|}ntdtj|}|d }|S) z Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format. Returns: `PIL.Image.Image`: A PIL Image. Zvisionzhttp://zhttps://T)streamzIIncorrect path or url, URLs must start with `http://` or `https://`, and z is not a valid pathzdIncorrect format used for image. Should be an url linking to an image, a local path, or a PIL image.RGB)r load_imager!str startswithr"r#openrequestsgetrawospathisfiler3ZImageOpsZexif_transposeconvert)r8rrrr\s"      r\c@seZdZdZddZdddZddZeje e e fejd d d Z dd dZ ddZdddZd ddZddZddZd!ddZdS)"ImageFeatureExtractionMixinzD Mixin that contain utilities for preparing image features. cCs4t|tjjtjfs0t|s0tdt|ddS)Nz Got type zS which is not supported, only `PIL.Image.Image`, `np.array` and `torch.Tensor` are.)r!r"r#r'r(rr3r4selfr8rrr_ensure_format_supported(sz4ImageFeatureExtractionMixin._ensure_format_supportedNcCs||t|r|}t|tjr|dur@t|jdtj}|jdkrf|j ddvrf| ddd}|rr|d}| tj }t j|S|S)a" Converts `image` to a PIL Image. Optionally rescales it and puts the channel dimension back as the last axis if needed. Args: image (`PIL.Image.Image` or `numpy.ndarray` or `torch.Tensor`): The image to convert to the PIL Image format. rescale (`bool`, *optional*): Whether or not to apply the scaling factor (to make pixel values integers between 0 and 255). Will default to `True` if the image type is a floating type, `False` otherwise. Nrr.r;r r9)rjrnumpyr!r'r(flatZfloatingr2r< transposeastypeZuint8r"r#Z fromarray)rir8rescalerrr to_pil_image/s    z(ImageFeatureExtractionMixin.to_pil_imagecCs&||t|tjjs|S|dS)z Converts `PIL.Image.Image` to RGB format. Args: image (`PIL.Image.Image`): The image to convert. r[)rjr!r"r#rfrhrrr convert_rgbMs z'ImageFeatureExtractionMixin.convert_rgb)r8scaler0cCs||||S)z7 Rescale a numpy image by scale amount )rj)rir8rsrrrrp[s z#ImageFeatureExtractionMixin.rescaleTcCs||t|tjjr"t|}t|r2|}|durLt|jdtj n|}|rh| | tj d}|r|j dkr|ddd}|S)a Converts `image` to a numpy array. Optionally rescales it and puts the channel dimension as the first dimension. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to convert to a NumPy array. rescale (`bool`, *optional*): Whether or not to apply the scaling factor (to make pixel values floats between 0. and 1.). Will default to `True` if the image is a PIL Image or an array/tensor of integers, `False` otherwise. channel_first (`bool`, *optional*, defaults to `True`): Whether or not to permute the dimensions of the image to put the channel dimension first. Nrp?r.r9r )rjr!r"r#r'r6rrlrmintegerrprofloat32r2rn)rir8rp channel_firstrrrr7bs  z*ImageFeatureExtractionMixin.to_numpy_arraycCsB||t|tjjr|St|r0|d}ntj|dd}|S)z Expands 2-dimensional `image` to 3 dimensions. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to expand. r)Zaxis)rjr!r"r#rZ unsqueezer' expand_dimsrhrrrrxs  z'ImageFeatureExtractionMixin.expand_dimsFcCs@||t|tjjr(|j|dd}n>|rft|tjrN||tj d}nt |rf|| d}t|tjrt|tjst ||j }t|tjst ||j }n| | fn| | f}|j ||dS)a Resizes `image`. Enforces conversion of input to PIL.Image. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to resize. size (`int` or `Tuple[int, int]`): The size to use for resizing the image. If `size` is a sequence like (h, w), output size will be matched to this. If `size` is an int and `default_to_square` is `True`, then image will be resized to (size, size). If `size` is an int and `default_to_square` is `False`, then smaller edge of the image will be matched to this number. i.e, if height > width, then image will be rescaled to (size * height / width, size). resample (`int`, *optional*, defaults to `PILImageResampling.BILINEAR`): The filter to user for resampling. default_to_square (`bool`, *optional*, defaults to `True`): How to convert `size` when it is a single int. If set to `True`, the `size` will be converted to a square (`size`,`size`). If set to `False`, will replicate [`torchvision.transforms.Resize`](https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.Resize) with support for resizing only the smallest edge and providing an optional `max_size`. max_size (`int`, *optional*, defaults to `None`): The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than `max_size` after being resized according to `size`, then the image is resized again so that the longer edge is equal to `max_size`. As a result, `size` might be overruled, i.e the smaller edge may be shorter than `size`. Only used if `default_to_square` is `False`. Returns: image: A resized `PIL.Image.Image`. Nr rz max_size = zN must be strictly greater than the requested size for the smaller edge size = )resample)PILImageResamplingZBILINEARrjr!r"r#rqr*r+intrKsizer3resize) rir8rr}Zdefault_to_squaremax_sizewidthheightshortlongZrequested_new_shortZ new_shortZnew_longrrrrs4   $    z"ImageFeatureExtractionMixin.resizecCs||t|ts||f}t|s0t|tjrp|jdkrD||}|jddvr`|jddn |jdd}n|j d|j df}|d|dd}||d}|d|dd}||d}t|t j j r| ||||fS|jddvrdnd}|s4t|tjr| ddd}t|r4|ddd}|dkrz||dkrz|dkrz||dkrz|d||||fS|jdd t|d|dt|d|df} t|tjrtj|| d } nt|r|| } | d |dd} | |d} | d |dd} | |d}|| d| | | |f<|| 7}|| 7}|| 7}|| 7}| dtd|t| jd |td|t| jd |f} | S) a Crops `image` to the given size using a center crop. Note that if the image is too small to be cropped to the size given, it will be padded (so the returned result has the size asked). Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor` of shape (n_channels, height, width) or (height, width, n_channels)): The image to resize. size (`int` or `Tuple[int, int]`): The size to which crop the image. Returns: new_image: A center cropped `PIL.Image.Image` or `np.ndarray` or `torch.Tensor` of shape: (n_channels, height, width). r9rr;r NTF.rB)r<rC)rjr!r+rr'r(r2rxr<rr"r#ZcroprnZpermutemaxZ zeros_likeZ new_zerosmin)rir8rZ image_shapetopZbottomleftrightrwZ new_shapeZ new_imageZtop_padZ bottom_padZleft_padZ right_padrrr center_cropsP    ,   02    4z'ImageFeatureExtractionMixin.center_cropcCs>||t|tjjr"||}|dddddddfS)a Flips the channel order of `image` from RGB to BGR, or vice versa. Note that this will trigger a conversion of `image` to a NumPy array if it's a PIL Image. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image whose color channels to flip. If `np.ndarray` or `torch.Tensor`, the channel dimension should be first. NrC)rjr!r"r#r7rhrrrflip_channel_orderRs  z.ImageFeatureExtractionMixin.flip_channel_orderrcCsL|dur |ntjj}||t|tjjs6||}|j||||||dS)a Returns a rotated copy of `image`. This method returns a copy of `image`, rotated the given number of degrees counter clockwise around its centre. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to rotate. If `np.ndarray` or `torch.Tensor`, will be converted to `PIL.Image.Image` before rotating. Returns: image: A rotated `PIL.Image.Image`. N)r}expandcenter translate fillcolor)r"r#ZNEARESTrjr!rqrotate)rir8Zangler}rrrrrrrrcs    z"ImageFeatureExtractionMixin.rotate)N)NT)F)NTN)NrNNN)rrr__doc__rjrqrrr'r(rryrrpr7rxr|rrrrrrrrrg#s   . CKrg)r.)N)sD  (    '   $$#