j x d dl Z d dlmZ d dlmZ d dlZd dlmZ ddl m
Z
ddl m Z m
Z
dgZ G d de
ZdS ) N)Any)tqdm )
VisionDataset)convert_target_to_relativecrop_bboxes_from_imageSVTc
Z e Zd ZdZdZdZ ddededed ed
ed d f fd
Zd e fdZ
xZ S )r a SVT dataset from `"The Street View Text Dataset - UCSD Computer Vision"
`_.
.. image:: https://doctr-static.mindee.com/models?id=v0.5.0/svt-grid.png&src=0
:align: center
>>> from doctr.datasets import SVT
>>> train_set = SVT(train=True, download=True)
>>> img, target = train_set[0]
Args:
train: whether the subset should be the training one
use_polygons: whether polygons should be considered as rotated bounding box (instead of straight ones)
recognition_task: whether the dataset should be used for recognition task
detection_task: whether the dataset should be used for detection task
**kwargs: keyword arguments from `VisionDataset`.
z,http://www.iapr-tc11.org/dataset/SVT/svt.zip@63b3d55e6b6d1e036e2a844a20c034fe3af3c32e4d914d6e0c4a3cd43df3bebfTFtrain use_polygonsrecognition_taskdetection_taskkwargsreturnNc t j | j d | j dfd|st nd i| |r|rt d || _ g | _ t j }| j r%t j | j
d n| j
}| j r2t j t j |d n1t j t j |d }| } t# | dt% | D ]}
|
\ } } } }
}t j t j || j s5t+ d t j || j |r
d
|D }n d |D }t j || }d
|D }|rt/ t j || j | }t1 || D ]Z\ }}|j d dk rD|j d dk r3t% | dk r d|vr | j ||f [b|r#| j | j |f | j | j t7 || f || _
d S )NTpre_transformsz`recognition_task` and `detection_task` cannot be set to True simultaneously. To get the whole dataset with boxes and labels leave both parameters to False.svt1z train.xmlztest.xmlzPreparing and Loading SVT)iterabledesctotalzunable to locate c g | ]=}t |j d t |j d gt |j d t |j d z t |j d gt |j d t |j d z t |j d t |j d z gt |j d t |j d t |j d z gg?S xywidthheightfloatattrib.0rects U/var/www/html/Carbon-Document/venv/lib/python3.11/site-packages/doctr/datasets/svt.py
z SVT.__init__..U s t{3 /00% C8H2I2IJ t{3 /005W9M3N3NNPUVZVabeVfPgPgh !$+c"2 3 3eDK.c s dk# .// dk# .// dk# .//% G8L2M2MM dk# .//% H8M2N2NN r& )dtypec & g | ]}|D ] }|j
S )text)r" r# labs r$ r% z SVT.__init__..o s' FFF4FF#chFFFFr& )img_pathgeomsr r )boxeslabels) super__init__URLSHA256r
ValueErrorr datanpfloat32ospathjoinrootETparsegetrootr lenexistsr+ FileNotFoundErrorasarrayr zipshapeappenddict)selfr r
r r r np_dtypetmp_rootxml_treexml_rootimagename_ _resolution
rectangles_boxesr0 r1 cropscroplabel __class__s r$ r3 z SVT.__init__) s+ H K
>NW55SW
c
VX : 7;kP27<< 6222ty z
>BHRW\\(K88 9 9 9"',,x<<==
##%%82MUXYaUbUbccc - P - PE27 /D!Q Z 7>>"',,x"C"CDD
a'(_BGLLSWS\<]<](_(_```
!+ !+ !#
6 B B BEFF:FFFF
P. Xty8Y8Yafggg#&uf#5#5 8 8KD%z!}q((TZ]Q->->3u::PQ>>VYafVfVf (($ 7778
P $)U!34444 $)Tf-M-M-M!NOOOO r& c d| j S )Nztrain=)r )rI s r$
extra_reprzSVT.extra_repr} s $
$$$r& )TFFF) __name__
__module__ __qualname____doc__r4 r5 boolr r3 strrY
__classcell__)rW s @r$ r r s $ 9C
OF "!& $ R R R R R
R
R
R R R R R R h%C % % % % % % % %r& )r: typingr defusedxml.ElementTree ElementTreer> numpyr8 r datasetsr utilsr r __all__r r* r& r$ rh s
# # # # # # # # # # # # E E E E E E E E 'k% k% k% k% k%- k% k% k% k% k%r&