j `ddlZddlmZddlmZddlmZddlmZdgZGddeZ dS) N)sample)Any)tqdm)AbstractDatasetIIITHWSc HeZdZdZ d dededededdf fd Zdefd ZxZ S) ralIIITHWS dataset from `"Generating Synthetic Data for Text Recognition" `_ | `"repository" `_ | `"website" `_. >>> # NOTE: This is a pure recognition dataset without bounding box labels. >>> # NOTE: You need to download the dataset. >>> from doctr.datasets import IIITHWS >>> train_set = IIITHWS(img_folder="/path/to/iiit-hws/Images_90K_Normalized", >>> label_path="/path/to/IIIT-HWS-90K.txt", >>> train=True) >>> img, target = train_set[0] >>> test_set = IIITHWS(img_folder="/path/to/iiit-hws/Images_90K_Normalized", >>> label_path="/path/to/IIIT-HWS-90K.txt") >>> train=False) >>> img, target = test_set[0] Args: img_folder: folder with all the images of the dataset label_path: path to the file with the labels train: whether the subset should be the training one **kwargs: keyword arguments from `AbstractDataset`. T img_folder label_pathtrainkwargsreturnNc tj|fi|tj|rtj|s3t dtj|s|n|g|_||_t|5}| }dddn #1swxYwYt|t|}tt|dz}|jrt|nt|d}t||dt||D]]} | dd\} } tj|| } |j| | f^dS)Nzunable to locate g?zPreparing and Loading IIITHWS)iterabledesctotalr)super__init__ospathexistsFileNotFoundErrordatar open readlinesrlenintslicersplitjoinappend) selfr r r r f annotations train_samples set_slice annotationimg_pathlabel __class__s Y/var/www/html/Carbon-Document/venv/lib/python3.11/site-packages/doctr/datasets/iiithws.pyrzIIITHWS.__init__)s ..v...w~~j)) x 1K1K x#$v"'..YcJdJd8t jt$v$vww w+-  *   (++--K ( ( ( ( ( ( ( ( ( ( ( ( ( ( ([#k*:*:;; C ,,s233 ,0JVE-(((E-QUr<s  %%%%%% +9%9%9%9%9%o9%9%9%9%9%r/