jnddlZddlZddlmZddlmZddlmZddlmZddl m Z m Z ddl Z ddlmZddlmZddlmZmZmZd d lmZgd Ze d Z d(dedededefdZdededeefdZde jeezdedefdZ d)deedededzdededzdedzde!de jfd Z"d!ed"e je#ee fzde$ee#ee fe jzffd#Z%d$eezd%e jdee jfd&Z&d"e$e jefde$e je#eefffd'Z'dS)*N)Sequence)partial)Path)AnyTypeVar)Image) get_img_shape)convert_to_relative_coords extract_cropsextract_rcrops)VOCABS) translate encode_stringdecode_sequenceencode_sequencespre_transform_multiclasscrop_bboxes_from_imageconvert_target_to_relative ImageTensor■ input_string vocab_name unknown_charreturncFtj|tdd}|D]x}|t|vrb|tjvr t jd|ddd}|dks|t|vr|}||z }y|S)a,Translate a string input in a given vocabulary Args: input_string: input string to translate vocab_name: vocabulary to use (french, latin, ...) unknown_char: unknown character for non-translatable characters Returns: A string translated in a given vocab Nz.output vocabulary must be in vocabs dictionaryNFDasciiignore) rgetKeyErrorstring whitespace unicodedata normalizeencodedecode)rrr translatedchars W/var/www/html/Carbon-Document/venv/lib/python3.11/site-packages/doctr/datasets/utils.pyrr#sz*%GHHHJ   vj) ) )v((((55<z!encode_string..Us#LLL$$e:K:K:K:K:Kr,z,Some characters cannot be found in 'vocab': z!. Please check the input string `z` and the vocabulary ``N)listmapindex ValueErrorset)rr-e missing_charss ` r+rrEsC \22333 LLLL,LLL  [3};M;M [ [.: [ [RW [ [ [   s!% A)5A$$A) input_seqmappingcxt|ttjfst dt|tjrI|jtjks%|t|krtdd t|j |S)aGiven a predefined mapping, decode the sequence of numbers to a string Args: input_seq: array to decode mapping: vocabulary (string), the encoding is given by the indexing of the character sequence Returns: A string, decoded from input_seq zInvalid sequence typez>Input must be an array of int, with max less than mapping sizer) isinstancernpndarray TypeErrordtypeint_maxlenAssertionErrorjoinr5 __getitem__)r;r<s r+rr\s i(BJ!7 8 81/000)RZ((_io.H.HIMMOO_bcj_k_kLkLk]^^^ 773w*I66 7 77r,F sequences target_sizeeossospaddynamic_seq_lengthc td|cxkrt|krnntdt|tr|rwt d|Ddz}t|tr|dz }t|tr|dz }t|ts|nt ||}t|tr/d|cxkrt|krnntd|}n|}t jt||g|t j} tttt||D]v\} } t|tr| || dt t| || | dt t| |f<wt|trJd|cxkrt|krnntd t j| d} || dddf<| S) agEncode character sequences using a given vocab as mapping Args: sequences: the list of character sequences of size N vocab: the ordered vocab to use for encoding target_size: maximum length of the encoded data eos: encoding of End Of String sos: optional encoding of Start Of String pad: optional encoding for padding. In case of padding, all sequences are followed by 1 EOS then PAD dynamic_seq_length: if `target_size` is specified, uses it as upper bound and enables dynamic sequence size Returns: the padded encoded data as a tensor rzz#encode_sequences..s(33AQ333333r,r zintrDminr?fullint32 enumerater5rrappendroll) rJr-rKrLrMrNrO max_lengthdefault_symbol encoded_dataidxseqs r+rrqsY. C#e**WXXX k3 ' 'g+=g3333333a7 c3    !OJ c3    !OJ(2;(D(Dfjj#jZeJfJf #s  c%jj [\\ \!wI 'Dn\^\deeeLc'-u"E"E"EyQQRR\\S c3    JJsOOO:=>ZCHHk@Z@Z>Z:[ S6CC+666677#s!  c%jj [\\ \w|Q//  QQQT r,imgtargetct|tjrt|t |}n&t|dt ||d<||fS)aConverts target to relative coordinates Args: img: tf.Tensor or torch.Tensor representing the image target: target to convert to relative coordinates (boxes (N, 4) or polygons (N, 4, 2)) Returns: The image and the target in relative coordinates boxes)r>r?r@r r )rarbs r+rrs\&"*%%Z+FM#4F4FGG4VG_mTWFXFXYYw ;r,img_pathgeomsctj|5}tj|d}dddn #1swxYwY|jdkr<|jdddkr)t||tS|jdkr:|jddkr)t||tStd ) zCrop a set of bounding boxes from an image Args: img_path: path to the image geoms: a array of polygons of shape (N, 4, 2) or of straight boxes of shape (N, 4) Returns: a list of cropped images RGBNr )rTrkrjzInvalid geometry format) ropenr?asarrayconvertndimshaper astyperUr r7)rerfpil_imgras r+rrs H  =*W__U%;%;<<=============== zQ5;qrr?f44c5<Q..S%,,S,"9"9::: . / //s(A  A A cJt|dt|}|d}dtt|D}t ||D] \}}|||!d|D}||fS)zConverts multiclass target to relative coordinates. Args: img: Image target: tuple of target polygons and their classes names Returns: Image and dictionary of boxes, with class names as keys rr ci|]}|gSr0r0)r1ks r+ z,pre_transform_multiclass..sBBB!2BBBr,cBi|]\}}|tj|dS)r)axis)r?stack)r1ruvs r+rvz,pre_transform_multiclass..s-HHHTQ!RXaa(((HHHr,)r r sortedr8ziprZitems)rarbrd boxes_classes boxes_dictrupolys r+rrs 'vay-2D2D E EE1IMBBvc-.@.@'A'ABBBJ}e,,##41 T""""HHZ5E5E5G5GHHHJ  ?r,)r)NrINNF)(r#r%collections.abcr SequenceType functoolsrpathlibrtypingrrnumpyr?PILrdoctr.io.imager doctr.utils.geometryr r r vocabsr__all__rstrrr4rUrr@rboolrdicttuplerrrr0r,r+rs  $$$$$$444444((((((ZZZZZZZZZZ   gm$$  D  #Y.8zL--8 8 88880#$99Cy9 9t9 9 t 9 t 99Z9999x  j4S>9 ;S#X3 34&0S4Z0 0tBJGW0000(% D0@*AeBJX\]`bf]fXgLgFhr,