#jddlZddlZddlmZddlmZmZddlmZddl m Z m Z ddl Z ddl ZddlmZmZmZmZmZmZmZmZmZddlmZmZmZmZmZmZdd l m!Z!erddl"Z#ddl$Z#e#j%j&Z'er}dd l(m)Z)m*Z*dd l+m,Z,dd l-m.Z.e'j/e,j0e'j1e,j1e'j2e,j2e'j3e,j3e'j4e,j4e'j5e,j5iZ6d e67DZ8niZ6iZ8erddl9Z9ej:e;Zde>ej=e>dfZ?GddeZ@GddeZAeBeCeDeCze>eBzfZEdZFGddeZGdZHdZIde>fdZJdZKdZLdZMdej=deNfd ZOdZd"eDde>e?fd#ZP dZde>e?e?zd"eDde?fd$ZQ dZde>e?e?zd"eDde>e?fd%ZRdej=fd&ZS d[dej=d'eDeTeDd(fzdzde@fd)ZUd[dej=d*e@eCzdzdeDfd+ZVd[dej=d,e@dzdeTeDeDffd-ZWd.eTeDeDfd/eDd0eDdeTeDeDffd1ZXd2ee de>e fd3ZYe@jZfde>e dej=fd*eCe@zde>eDfd4Z[d5eBeCe>eTzfdeNfd6Z\d5eBeCe>eTzfdeNfd7Z]d8eeBeCe>eTzfdeNfd9Z^d8eeBeCe>eTzfdeNfd:Z_ d[de eCdfd;e`dzddfd<Zae!d=> d[de eCdfd;e`dzddfd?Zb d[de e>eTeCdfd;e`dzde de>de>e>dffd@Zc d\dAeNdzdBe`dzdCeNdzdDe`e>e`zdzdEe`e>e`zdzdFeNdzdGeBeCeDfeDzdzdHeNdzdIeBeCeDfdzdJeNdzdKeBeCeDfdzdLe dMdNeDfdzfdOZdGdPdQZedReAdSeTeAd(fd8e>eBddfdTZfdUe>eCdVe>eCfdWZgeGdXdYZhdS)]N)Iterable) dataclassfields)BytesIO)AnyUnion) ExplicitEnumis_numpy_arrayis_torch_availableis_torch_tensoris_torchvision_availableis_vision_availableloggingrequires_backendsto_numpy)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDIMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDOPENAI_CLIP_MEANOPENAI_CLIP_STD)requires) ImageReadMode decode_image)InterpolationMode) pil_to_tensorci|]\}}|| Sr).0kvs b/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/transformers/image_utils.py r$Cs&`&`&`1q!&`&`&`zPIL.Image.Imagez torch.TensorceZdZdZdZdS)ChannelDimensionchannels_first channels_lastN)__name__ __module__ __qualname__FIRSTLASTrr%r#r'r'Us E DDDr%r'ceZdZdZdZdS)AnnotationFormatcoco_detection coco_panopticN)r*r+r,COCO_DETECTION COCO_PANOPTICrr%r#r0r0Zs%N#MMMr%r0c\tot|tjjSN)r isinstancePILImageimgs r# is_pil_imager<bs!  EZSY_%E%EEr%ceZdZdZdZdZdS) ImageTypepillowtorchnumpyN)r*r+r,r8TORCHNUMPYrr%r#r>r>fs C E EEEr%r>ct|r tjSt|r tjSt |r tjStdt|)NzUnrecognized image type ) r<r>r8r rBr rC ValueErrortypeimages r#get_image_typerIlsgE}ue =U == > >>r%c\t|pt|pt|Sr6)r<r r r:s r#is_valid_imagerKvs*    Ks 3 3 Ks7K7KKr%imagesc8|otd|DS)Nc34K|]}t|VdSr6)rKr rHs r# z*is_valid_list_of_images..{s*DDE.//DDDDDDr%all)rLs r#is_valid_list_of_imagesrSzs$  DcDDVDDDDDDr%c,t|dtr d|DSt|dtjrtj|dSt|dt jrt j|dSdS)Nrcg|] }|D]}| Srr)r sublistitems r# z$concatenate_list..s%CCC7CC4CCCCr%axis)dim)r7listnpndarray concatenater@Tensorcat) input_lists r#concatenate_listrc~s*Q-&&,CCJCCCC JqM2: . .,~jq1111 JqM5< 0 0,y++++,,r%ct|ttfr|D]}t|sdSnt |sdSdS)NFT)r7r\tuple valid_imagesrK)imgsr;s r#rfrfsd$u &&  C$$ uu  D ! !u 4r%cht|ttfrt|dSdS)NrF)r7r\rerKr:s r# is_batchedris/#e}%%&c!f%%% 5r%rHreturnc|jtjkrdStj|dkotj|dkS)zV Checks to see whether the pixel values have already been rescaled to [0, 1]. Frr )dtyper]uint8minmaxrGs r#is_scaled_imagerps? {bhu 6%==A  4"&--1"44r%expected_ndimsc Ft|r|St|r|gSt|rP|j|dzkrt |}n0|j|kr|g}n!t d|dzd|d|jd|St dt |d)a Ensure that the output 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.z]Invalid image type. Expected either PIL.Image.Image, numpy.ndarray, or torch.Tensor, but got .)rir<rKndimr\rErFrLrrs r#make_list_of_imagesrws& Fxf  ;.1, , ,&\\FF [N * *XFF.8J..P^..K...  whlmshthtwww  r%cRt|ttfr>td|Dr%td|Dr d|DSt|ttfrWt |rHt |ds|dj|kr|S|dj|dzkr d|DSt|r:t |s |j|kr|gS|j|dzkrt|Std|)a Ensure that the output is a flat list of images. If the input is a single image, it is converted to a list of length 1. If the input is a nested list of images, it is converted to a flat list of images. Args: images (`Union[list[ImageInput], ImageInput]`): The input image. expected_ndims (`int`, *optional*, defaults to 3): The expected number of dimensions for a single input image. Returns: list: A list of images or a 4d array of images. c3NK|] }t|ttfV!dSr6r7r\rer images_is r#rPz+make_flat_list_of_images..0KK 8dE]33KKKKKKr%c3:K|]}t|p| VdSr6rSr{s r#rPz+make_flat_list_of_images..2YYh'11A\YYYYYYr%cg|] }|D]}| Srrr img_listr;s r#rXz,make_flat_list_of_images..s%???h??s????r%rr cg|] }|D]}| Srrrs r#rXz,make_flat_list_of_images..s%CCCH(CC3CCCCCr%z*Could not make a flat list of images from r7r\rerRrSr<rurKrErvs r#make_flat_list_of_imagesrsX" 6D%=))@ KKFKKK K K@ YYRXYYY Y Y@ @?F????&4-((D-DV-L-LD q " " fQin&F&FM !9>^a/ / /CCCCC Cf    6;.#@#@8O ;.1, , ,<<  J&JJ K KKr%c>t|ttfr4td|Drtd|Dr|St|ttfrXt |rIt |ds|dj|kr|gS|dj|dzkr d|DSt|r.r}r%c3:K|]}t|p| VdSr6rr{s r#rPz-make_nested_list_of_images..rr%rr c,g|]}t|Sr)r\rOs r#rXz.make_nested_list_of_images.. s444EDKK444r%z]Invalid input type. Must be a single image, a list of images, or a list of batches of images.rrvs r#make_nested_list_of_imagesrsF 6D%=)) KKFKKK K K YYRXYYY Y Y  &4-((5-DV-L-L5 q " " fQin&F&F8O !9>^a/ / /44V444 4f"    6;.#@#@H:  ;.1, , ,LL> ! t u uur%ct|stdt|tr3t |t jjrtj|St|S)NzInvalid image type: ) rKrErFrr7r8r9r]arrayrr:s r#to_numpy_arrayrsl #  =;S ;;<<<C!A!Ax}} C==r% num_channels.c||nd}t|tr|fn|}|jdkrd\}}n9|jdkrd\}}n(|jdkrd\}}ntd|j|j||vr>|j||vr/t d |jd tjS|j||vr tjS|j||vr tj Std ) a[ Infers the channel dimension format of `image`. Args: image (`np.ndarray`): The image to infer the channel dimension of. num_channels (`int` or `tuple[int, ...]`, *optional*, defaults to `(1, 3)`): The number of channels of the image. Returns: The channel dimension of the image. Nr rqrq)r)rrz(Unsupported number of image dimensions: z4The channel dimension is ambiguous. Got image shape z. Assuming channels are the first dimension. Use the [input_data_format](https://huggingface.co/docs/transformers/main/internal/image_processing_utils#transformers.image_transforms.rescale.input_data_format) parameter to assign the channel dimension.z(Unable to infer channel dimension format) r7intrurEshapeloggerwarningr'r-r.)rHr first_dimlast_dims r#infer_channel_dimension_formatr s/$0#;<<L&0s&C&CUL??L zQ" 88 q" 88 q" 88PEJPPQQQ {9--%+h2G<2W2W K5; K K K    %% Y < / /%% X , . .$$ ? @ @@r%input_data_formatc|t|}|tjkr |jdz S|tjkr |jdz St d|)a Returns the channel dimension axis of the image. Args: image (`np.ndarray`): The image to get the channel dimension axis of. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the image. If `None`, will infer the channel dimension from the image. Returns: The channel dimension axis of the image. Nrqr Unsupported data format: )rr'r-rur.rE)rHrs r#get_channel_dimension_axisrGsf :5AA,222zA~ .3 3 3zA~ D1BDD E EEr% channel_dimc|t|}|tjkr|jd|jdfS|tjkr|jd|jdfSt d|)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)rr'r-rr.rE)rHrs r#get_image_sizer]sz4U;; &,,,{2 B// (- - -{2 B//B[BBCCCr% image_size max_height max_widthc|\}}||z }||z }t||}t||z}t||z} || fS)a Computes the output image size given the input image and the maximum allowed height and width. Keep aspect ratio. Important, even if image_height < max_height and image_width < max_width, the image will be resized to at least one of the edges be equal to max_height or max_width. For example: - input_size: (100, 200), max_height: 50, max_width: 50 -> output_size: (25, 50) - input_size: (100, 200), max_height: 200, max_width: 500 -> output_size: (200, 400) Args: image_size (`tuple[int, int]`): The image to resize. max_height (`int`): The maximum allowed height. max_width (`int`): The maximum allowed width. )rnr) rrrheightwidth height_scale width_scale min_scale new_height new_widths r##get_image_size_for_max_height_widthrus_,MFE&Le#KL+..IVi'((JEI%&&I y  r%valuesc(dt|DS)zO Return the maximum value across all indices of an iterable of values. c,g|]}t|Sr)ro)r values_is r#rXz&max_across_indices..s 7 7 7hCMM 7 7 7r%)zip)rs r#max_across_indicesrs 8 7#v, 7 7 77r%c|tjkrtd|D\}}}n@|tjkrtd|D\}}}nt d|||fS)zH Get the maximum height and width across all images in a batch. cg|] }|j Srrr r;s r#rXz(get_max_height_width..6S6S6SSsy6S6S6Sr%cg|] }|j Srrrs r#rXz(get_max_height_width..rr%z"Invalid channel dimension format: )r'r-rr.rE)rLr_rrs r#get_max_height_widthrs ,222#56S6SF6S6S6S#T#T :yy .3 3 3#56S6SF6S6S6S#T#T IqqQ>OQQRRR  ""r% annotationct|trfd|vrbd|vr^t|dttfrWXY>Z\`3a3a /t 5r%ct|trjd|vrfd|vrbd|vr^t|dttfr.s+NN31#66NNNNNNr%rQrs r# valid_coco_detection_annotationsrs NN+NNN N NNr%c4td|DS)Nc34K|]}t|VdSr6)rrs r#rPz2valid_coco_panoptic_annotations..s+MM#055MMMMMMr%rQrs r#valid_coco_panoptic_annotationsrs MMMMM M MMr%timeoutc ttdgt|tr\|ds|drHt jttj ||dj }ntj |r t j|}n|dr|dd} t!j|}t jt|}nU#t&$r}t)d |d |d }~wwxYwt|t jjst+d t j|}|d }|S)a3 Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format. timeout (`float`, *optional*): The timeout value in seconds for the URL request. Returns: `PIL.Image.Image`: A PIL Image. visionhttp://https://Trfollow_redirects data:image/,r Incorrect image source. Must be a valid URL starting with `http://` or `https://`, a valid path to an image file, or a base64 encoded string. Got . Failed with NzuIncorrect format used for image. Should be an url linking to an image, a base64 string, a local path, or a PIL image.RGB)r load_imager7str startswithr8r9openrhttpxgetcontentospathisfilesplitbase64 decodebytesencode ExceptionrE TypeErrorImageOpsexif_transposeconvert)rHrb64es r#rrs j8*---%   I & & %*:*::*F*F INN759UG^b+c+c+c+k#l#lmmEE W^^E " " INN5))EE .. , C((+ (88 ws||44    BjoBB@BB sy / /  D    L ' ' . .E MM% E LsAE"" F,FF) torchvision)backendscddl}t|tr}|ds|dr[t j||dj}|jt||j }t|tj Stj|rt|tj S|d r|d d } t#j|}n'#t($r}t+d |d |d}~wwxYw|jt||j }t|tj St|t,jjrAt,j|}t5|dSt9d)at Loads `image` directly to a `torch.Tensor` using torchvision. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format. timeout (`float`, *optional*): The timeout value in seconds for the URL request. Returns: `torch.Tensor`: A `[C, H, W]` uint8 tensor in RGB channel order. rNrrTr)rl)moderrr rrrz`Incorrect format used for image. Should be a URL, a local path, a base64 string, or a PIL image.)r@r7rrrrr frombuffer bytearrayrmrrrrrrrrrrrrEr8r9rrrrr)rHrr@rawbufrs r#load_image_as_tensorrs"LLL%   I & & =%*:*::*F*F =)E7TJJJRC"%"9S>>EEEC-*;<<< < W^^E " " =M,=>>> > .. , C((+ (88    BjoBB@BB #%"9S>>EEEC-*;<<< < E39? + +  ++E22U]]511222 n   s &D22 E<EEct|ttfrMt|r0t|dttfrfd|DSfd|DSt |S)aLoads images, handling different levels of nesting. Args: images: A single image, a list of images, or a list of lists of images to load. timeout: Timeout for loading images. Returns: A single image, a list of images, a list of lists of images. rc,g|]}fd|DS)c2g|]}t|Srrr rHrs r#rXz*load_images...:s&QQQEZw777QQQr%r)r image_grouprs r#rXzload_images..:s/lllVaQQQQ[QQQlllr%c2g|]}t|Srrrs r#rXzload_images..<s&KKK5Jug666KKKr%r)r7r\rerr)rLrs `r# load_imagesr ,s&4-((3 v;; L:fQi$?? Llllleklll lKKKKFKKK K&'2222r% do_rescalerescale_factor do_normalize image_mean image_stddo_padpad_sizedo_center_crop crop_size do_resizesizeresamplePILImageResamplingrc |r|td|r|td|r||td|r|td| r| | tddSdS)a Checks validity of typically used arguments in an `ImageProcessor` `preprocess` method. Raises `ValueError` if arguments incompatibility is caught. Many incompatibilities are model-specific. `do_pad` sometimes needs `size_divisor`, sometimes `size_divisibility`, and sometimes `size`. New models and processors added should follow existing arguments when possible. Nz=`rescale_factor` must be specified if `do_rescale` is `True`.zgDepending on the model, `size_divisor` or `pad_size` or `size` must be specified if `do_pad` is `True`.zP`image_mean` and `image_std` must both be specified if `do_normalize` is `True`.z<`crop_size` must be specified if `do_center_crop` is `True`.zA`size` and `resample` must be specified if `do_resize` is `True`.)rE) r r r r rrrrrrrrs r#validate_preprocess_argumentsrAs,Zn,XYYY  (" u   m+y/@klllY)+WXXX^$*x/C\]]]^^/C/Cr%ceZdZdZdZddZdZdejde e zdejfd Z dd Z d Z ddZddZdZdZddZdS)ImageFeatureExtractionMixinzD Mixin that contain utilities for preparing image features. ct|tjjtjfs/t |s"t dt|ddSdS)Nz Got type zU which is not supported, only `PIL.Image.Image`, `np.ndarray` and `torch.Tensor` are.)r7r8r9r]r^r rErFselfrHs r#_ensure_format_supportedz4ImageFeatureExtractionMixin._ensure_format_supportedtsq%#)/2:!>?? X]H^H^ &DKK&&&     r%Nc||t|r|}t|tjr|%t|jdtj}|jdkr&|j ddvr| ddd}|r|dz}| tj }tj|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. Nrrqrr r)rr rAr7r]r^flatfloatingrur transposeastypermr8r9 fromarray)rrHrescales r# to_pil_imagez(ImageFeatureExtractionMixin.to_pil_image{s %%e,,, 5 ! ! "KKMME eRZ ( ( .$UZ]BK@@zQ5;q>V#;#;1a00 $ LL**E9&&u-- - r%c||t|tjjs|S|dS)z Converts `PIL.Image.Image` to RGB format. Args: image (`PIL.Image.Image`): The image to convert. r)rr7r8r9rrs r# convert_rgbz'ImageFeatureExtractionMixin.convert_rgbsE %%e,,,%11 L}}U###r%rHscalerjc6||||zS)z7 Rescale a numpy image by scale amount )r)rrHr*s r#r&z#ImageFeatureExtractionMixin.rescales" %%e,,,u}r%Tc||t|tjjrt j|}t |r|}|%t|jdtj n|}|r3| | 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?rqrr )rr7r8r9r]rr rAr!integerr&r$float32rur#)rrHr& channel_firsts r#rz*ImageFeatureExtractionMixin.to_numpy_arrays %%e,,, eSY_ - - $HUOOE 5 ! ! "KKMME;B?*UZ]BJ777PW  FLLbj!9!99EEE  -UZ1__OOAq!,,E r%c||t|tjjr|St |r|d}nt j|d}|S)z Expands 2-dimensional `image` to 3 dimensions. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to expand. rrY)rr7r8r9r unsqueezer] expand_dimsrs r#r3z'ImageFeatureExtractionMixin.expand_dimssq %%e,,, eSY_ - - L 5 ! ! 2OOA&&EEN5q111E r%Fc||t|tjjr||d}n|rt|t jr4||t j d}n7t|r(|| d}t|t jrt|t js,t j ||j }t|t js,t j ||j }nt|rddl}t||js;t|t jr|j|}n|j|}t||js;t|t jr|j|}n|j|}|jdkr-|jddvr||ddddfz |ddddfz S||z |z S)a  Normalizes `image` with `mean` and `std`. Note that this will trigger a conversion of `image` to a NumPy array if it's a PIL Image. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to normalize. mean (`list[float]` or `np.ndarray` or `torch.Tensor`): The mean (per channel) to use for normalization. std (`list[float]` or `np.ndarray` or `torch.Tensor`): The standard deviation (per channel) to use for normalization. rescale (`bool`, *optional*, defaults to `False`): Whether or not to rescale the image to be between 0 and 1. If a PIL image is provided, scaling will happen automatically. T)r&r-rNrqr)rr7r8r9rr]r^r&r$r/r floatrrlr@r` from_numpytensorrur)rrHmeanstdr&r@s r# normalizez%ImageFeatureExtractionMixin.normalizes6 %%e,,, eSY_ - - ?''t'<> eRZ ( ( ,dBJ// :x~~,,U[99c2:.. 8hsmm**5;77 U # # , LLLdEL11 .dBJ//.+5+D11DD'5<--Dc5<00 ,c2:..,*%*3//CC&%,s++C :??u{1~77DD$//3qqq$}3EE EDLC' 'r%c||n tj}||t|tjjs||}t|trt|}t|tst|dkr|r*t|tr||fn|d|df}n|j \}}||kr||fn||f\}} t|tr|n|d} || kr|S| t| | z|z } } |8|| krtd|d|| |krt|| z| z |} } ||kr| | fn| | f}| ||S)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 = )r)rBILINEARrr7r8r9r'r\rerrrrEresize) rrHrrdefault_to_squaremax_sizerrshortlongrequested_new_short new_shortnew_longs r#r=z"ImageFeatureExtractionMixin.resizes< (3889K9T %%e,,,%11 -%%e,,E dD ! ! ;;D dC  [CIINN  ['1$'<'<Td||47DQRGBT % v16&ufoovuo t.8s.C.C&Pdda#/// L&93?RUY?Y\a?a;b;b8 '#666(G(GG@DGG (**.1(Y2F2Q.R.RT\8 05 8,,hPYEZ||D8|444r%cV||t|ts||f}t|st|tjrN|jdkr||}|jddvr|jddn|jdd}n|j d|j df}|d|dz dz}||dz}|d|dz dz}||dz}t|tj j r| ||||fS|jddv}|sWt|tjr| ddd}t|r|ddd}|dkr-||dkr!|dkr||dkr|d||||fS|jddt|d|dt|d|dfz} t|tjrt j|| } n$t|r|| } | d|dz dz} | |dz} | d |dz dz} | |dz}|| d| | | |f<|| z }|| z }|| z }|| z }| 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). rrrr N.rrr)rr7rer r]r^rur3rrr8r9cropr#permutero zeros_like new_zerosrn)rrHr image_shapetopbottomleftrightr0 new_shape new_imagetop_pad bottom_padleft_pad right_pads r# center_cropz'ImageFeatureExtractionMixin.center_cropYsd %%e,,,$&& $1a7{1~- bMKN2q8{1~- AF #wz)8I+==> w'   Qs9?2#6???QPST]TcdfTginPoPoAo o r%c||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. Nr)rr7r8r9rrs r#flip_channel_orderz.ImageFeatureExtractionMixin.flip_channel_orders` %%e,,, eSY_ - - /''..ETTrT111aaaZ  r%rc||ntjj}||t |tjjs||}|||||||S)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)rexpandcenter translate fillcolor)r8r9NEARESTrr7r'rotate)rrHanglerrYrZr[r\s r#r^z"ImageFeatureExtractionMixin.rotates} (3889J %%e,,,%11 -%%e,,E|| HVFicl   r%r6)NT)F)NTN)NrNNN)r*r+r,__doc__rr'r)r]r^r5rr&rr3r:r=rUrWr^rr%r#rros < $ $ $RZ  @(2(2(2(2(hA5A5A5A5FIIIV!!!"      r%rannotation_formatsupported_annotation_formatsc||vrtdtd||tjurt |std|tjurt |stddSdS)NzUnsupported annotation format: z must be one of zInvalid COCO detection annotations. Annotations must a dict (single image) or list of dicts (batch of images) with the following keys: `image_id` and `annotations`, with the latter being a list of annotations in the COCO format.zInvalid COCO panoptic annotations. Annotations must a dict (single image) or list of dicts (batch of images) with the following keys: `image_id`, `file_name` and `segments_info`, with the latter being a list of annotations in the COCO format.)rEformatr0r3rr4r)rarbrs r#validate_annotationsres  <<<q6qqSoqqrrr,;;;/ << B  ,:::.{;; M ;:  r%valid_processor_keyscaptured_kwargsct|t|}|r5d|}td|ddSdS)Nz, zUnused or unrecognized kwargs: rt)set differencejoinrr)rfrg unused_keysunused_key_strs r#validate_kwargsrnspo&&11#6J2K2KLLKL;//JJJJKKKKKLLr%ceZdZUdZdZedzed<dZedzed<dZedzed<dZ edzed<dZ edzed<dZ edzed<d Z dd Z d Zd Zd ZdZdZddZdefdZdS)SizeDictz> Hashable dictionary to store image size information. Nrr longest_edge shortest_edgerrcht||rt||Std|d)NKey z not found in SizeDict.)hasattrgetattrKeyErrorrkeys r# __getitem__zSizeDict.__getitem__s> 4   &4%% %:c:::;;;r%cft||r t||t||S|Sr6rurv)rrydefaults r#rz SizeDict.gets8 4   &'$"4"4"@4%% %r%c#rKt|D]$}t||j}| |j|fV%dSr6)rrvname)rfvals r#__iter__zSizeDict.__iter__sN " "A$''Cfck!!! " "r%cht|j|j|j|j|j|jfSr6)hashrrrqrrrr)rs r#__hash__zSizeDict.__hash__ s/T[$*d.?ASUYUdfjftuvvvr%cFt||ot||duSr6r|rxs r# __contains__zSizeDict.__contains__s&tS!!DgdC&8&8&DDr%ct||std|dt|||dS)Nrtz" is not a valid field of SizeDict.)rurwobject __setattr__)rryvalues r# __setitem__zSizeDict.__setitem__sMtS!! KI#IIIJJ J4e,,,,,r%c2ttrtkSttrRtfdt Dtfdt DkSt S)Nc3BK|]}t|jVdSr6rvr)r rrs r#rPz"SizeDict.__eq__..s/EE1qv..EEEEEEr%c3BK|]}t|jVdSr6r)r rothers r#rPz"SizeDict.__eq__..sHOO+,qv&&OOOOOOr%)r7rrprerNotImplemented)rrs``r#__eq__zSizeDict.__eq__s eT " " '::& & eX & & EEEEt EEEEEOOOO06t OOOJJ r%rjct|ttzr=t|}|t|tdi|StS)Nr)r7rrpupdaterrrmergeds r#__or__zSizeDict.__or__!sU eTH_ - - &$ZZF MM$u++ & & &%%f%% %r%ct|tr3t|}|t||StSr6)r7rrrrs r#__ror__zSizeDict.__ror__(sB eT " " %[[F MM$t** % % %Mr%r6)rjrp)r*r+r,r`rr__annotations__rrqrrrrrzrrrrrrrrrrr%r#rprps=FC$JE3:#L#*### $M3:$$$!Jd !!! IsTz   <<<  """wwwEEE--- r%rp)rqr6) NNNNNNNNNNNN)irrcollections.abcr dataclassesrriortypingrrrrAr]utilsr r r r rrrrrutils.constantsrrrrrrutils.import_utilsr PIL.Imager8 PIL.ImageOpsr9 Resamplingrtorchvision.iorrtorchvision.transformsr!torchvision.transforms.functionalrr] NEAREST_EXACTBOXr<HAMMINGBICUBICLANCZOSpil_torch_interpolation_mappingitemstorch_pil_interpolation_mappingr@ get_loggerr*rr^r\ ImageInputr'r0rrrAnnotationTyper<r>rIrKrSrcrfriboolrprwrrrrerrrrrr-rrrrrr5rrr rrrernrprr%r#rs  $$$$$$))))))))                       )(((((.-)::::::::888888?????? "$5$C 1 5#%6%?"$5$="$5$="$5$= '#'a&`8W8]8]8_8_&`&`&`##&(#&(#LLL  H % %rz>48I3JDQSQ[L\^bcq^rr | $$$$$|$$$ c39tDz112FFF  ???LLLEDEEEE,,,    52:5$5555###D8x}8c8888braw # # ~rz12 3 #HKN^H^ # #Y # # # # 4TE\8I3J t     $sD5L7H2I d     O(4TE\@Q;R2SOX\OOOON$sD5L?P:Q1RNW[NNNN !** '' (* T\*****Z #$$$!* * '' (* T\* * * * %$* \QU33 $s$55 63AF3 d#45tDAR