ёi S SK Jr S SKrS SKrS SKJrJrJr S SKr S SK
J r S SK r S SK
Jr S SKJr \( a" S SKJr S SKJr S SKJr S S
KJr \S r\S r/ rS
r Sr Sr Sr Sr Sr!SSSS.r" " S S\\#S 5 r$g) ) annotationsN)
TYPE_CHECKINGAnyLiteral)Image)_check_exists_and_download)Dataset) DTypeLike)
_Transform )_ImageDataType)cv2piltrainvalidtestz=https://dataset.bj.bcebos.com/voc/VOCtrainval_11-May-2012.tar 6cd6e144f989b92b3379bac3b3de84fdz/VOCdevkit/VOC2012/ImageSets/Segmentation/{}.txtz#VOCdevkit/VOC2012/JPEGImages/{}.jpgz*VOCdevkit/VOC2012/SegmentationClass/{}.pngvoc2012trainvalr val)r r r c \ rS rSr% SrS\S' S\S' S\S' S \S
' S \S ' S
\S' S SS jjrS rSS jrSS jr SS jr
Sr g)VOC20126 a
Implementation of `VOC2012 `_ dataset.
Args:
data_file (str|None, optional): Path to data file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/voc2012.
mode (str, optional): Either train or test mode. Default 'train'.
transform (Callable|None, optional): Transform to perform on image, None for no transform. Default: None.
download (bool, optional): Download dataset automatically if :attr:`data_file` is None. Default: True.
backend (str|None, optional): Specifies which type of image to be returned:
PIL.Image or numpy.ndarray. Should be one of {'pil', 'cv2'}.
If this option is not set, will get backend from :ref:`paddle.vision.get_image_backend `,
default backend is 'pil'. Default: None.
Returns:
:ref:`api_paddle_io_Dataset`. An instance of VOC2012 dataset.
Examples:
.. code-block:: python
>>> # doctest: +TIMEOUT(120)
>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import VOC2012
>>> voc2012 = VOC2012()
>>> print(len(voc2012))
2913
>>> for i in range(5): # only show first 5 images
... img, label = voc2012[i]
... # do something with img and label
... print(type(img), img.size)
... # (500, 281)
... print(type(label), label.size)
... # (500, 281)
>>> transform = T.Compose(
... [
... T.ToTensor(),
... T.Normalize(
... mean=[0.5, 0.5, 0.5],
... std=[0.5, 0.5, 0.5],
... to_rgb=True,
... ),
... ]
... )
>>> voc2012_test = VOC2012(
... mode="test",
... transform=transform, # apply transform to every image
... backend="cv2", # use OpenCV as image transform backend
... )
>>> print(len(voc2012_test))
1464
>>> for img, label in itertools.islice(iter(voc2012_test), 5): # only show first 5 images
... # do something with img and label
... print(type(img), img.shape) # type: ignore
... # [3, 281, 500]
... print(type(label), label.shape)
... # (281, 500)
str | None data_file _DatasetModemode_Transform[Any, Any] | None transform
_ImageBackendbackendstrflagr
dtypeNc UR 5 S; d
SU 35 eUc [ R R 5 nUS; a [ SU 35 eXPl [ UR 5 U l Xl U R c. U( d S5 e[ U[ [ [ U5 U l X0l
U R 5 [ R " 5 U l g )Nr z3mode should be 'train', 'valid' or 'test', but got )r r z4Expected backend are one of ['pil', 'cv2'], but got z>data_file is not set and downloading automatically is disabled)lowerpaddlevisionget_image_backend
ValueErrorr"
MODE_FLAG_MAPr$ r r VOC_URLVOC_MD5 CACHE_DIRr
_load_annoget_default_dtyper% )selfr r r downloadr" s ^/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/vision/datasets/voc2012.py__init__VOC2012.__init__ s zz|
H A G H
? mm557G . ( FwiP
!$**,/ " >> !
P
8 87GY DN #
--/
c 0 U l [ R " U R 5 U l U R R 5 H nXR UR ' M [ R U R 5 nU R R U R U 5 n/ U l / U l U H nUR 5 n[ R UR S5 5 n[ R UR S5 5 nU R R# U5 U R R# U5 M g )Nzutf-8)name2memtarfileopenr data_tar
getmembersnameSET_FILEformatr$ extractfiledatalabelsstrip DATA_FILEdecode
LABEL_FILEappend)r2 eleset_filesetslinerB labels r4 r0 VOC2012._load_anno s
T^^4
==++-C&)MM#(( # . ??499-}}(( x)@A D::DHHUOE >> %>>$'D <<5 ;;tzz*ELL,DD D{r7 c , [ U R 5 $ N)lenrB r2 s r4 __len__VOC2012.__len__ s 499~ r7 c \ U R ( a U R R 5 g g r[ )r< closer] s r4 __del__VOC2012.__del__ s == MM ! r7 ) r" rB r r< r% r$ rC r9 r )Nr NTN) r r r r r r r3 boolr" z_ImageBackend | NonereturnNone)rV intre z'tuple[_ImageDataType, npt.NDArray[Any]])re rg )re rf ) __name__
__module__ __qualname____firstlineno____doc____annotations__r5 r0 rX r^ rb __static_attributes__ r7 r4 r r 6 s AF
**
I !% $15 (,
%0 %0 %0 / %0
%0 &
%0
%0N&&* "r7 r )r
znpt.NDArray[Any])%
__future__r rQ r: typingr r r numpyrS PILr r( paddle.dataset.commonr paddle.ior numpy.typingnptpaddle._typingr
#paddle.vision.transforms.transformsr imager
r! r __all__r- r. r? rE rG r/ r, tupler ro r7 r4 r} s # . .
< (>&L)M34L
I
, < 1
9
$gF
_"ge @AB _"r7