ёi% S SK Jr S SKJrJrJr \( a S SKJr S SKJ r SSK
J r J r \S r
S SKrS SKrS SKrS SKJr S SKrS S KJr S S
KJr S S KJr / rS r S
r Sr Sr Sr Sr!SSSS.r" " S S\\#S 5 r$g) ) annotations)
TYPE_CHECKINGAnyLiteralN)
_Transform )
_ImageBackend_ImageDataTypetrainvalidtest)Image)_check_exists_and_download)Dataset)
try_importz8http://paddlemodels.bj.bcebos.com/flowers/102flowers.tgzz9http://paddlemodels.bj.bcebos.com/flowers/imagelabels.matz3http://paddlemodels.bj.bcebos.com/flowers/setid.mat 52808999861908f626f3c1f4e79d11fa e0620be6f572b9609742df49c70aed4d a5357ecc9cb78c4bef273ce3793fc85ctstidtrnidr
)r r r
c \ rS rSr% SrS\S' S\S' S\S' S\S' S \S
' S \S ' S SS jjr SS jrS rSr g
)Flowers6 a
Implementation of `Flowers102 `_
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/flowers/.
label_file (str|None, optional): Path to label file, can be set None if
:attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/flowers/.
setid_file (str|None, optional): Path to subset index file, can be set
None if :attr:`download` is True. Default: None, default data path: ~/.cache/paddle/dataset/flowers/.
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|None, 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 Flowers dataset.
Examples:
.. code-block:: python
>>> # doctest: +TIMEOUT(60)
>>> import itertools
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import Flowers
>>> flowers = Flowers()
>>> print(len(flowers))
6149
>>> for i in range(5): # only show first 5 images
... img, label = flowers[i]
... # do something with img and label
... print(type(img), img.size, label)
... # (523, 500) [1]
>>> transform = T.Compose(
... [
... T.Resize(64),
... T.ToTensor(),
... T.Normalize(
... mean=[0.5, 0.5, 0.5],
... std=[0.5, 0.5, 0.5],
... to_rgb=True,
... ),
... ]
... )
>>> flowers_test = Flowers(
... mode="test",
... transform=transform, # apply transform to every image
... backend="cv2", # use OpenCV as image transform backend
... )
>>> print(len(flowers_test))
1020
>>> for img, label in itertools.islice(iter(flowers_test), 5): # only show first 5 images
... # do something with img and label
... print(type(img), img.shape, label) # type: ignore
... # [3, 64, 96] [1]
r backend
str | None data_file
label_file
setid_file _DatasetModemode_Transform[Any, Any] | None transformNc F UR 5 S; d
SU 35 eUc [ R R 5 nUS; a [ SU 35 eXpl [ UR 5 nU( d% U( d S5 e[ U[ [ SU5 nU( d% U( d S5 e[ U[ [ SU5 nU( d% U( d S5 e[ U[ [ SU5 nXPl [ R " U5 n UR# S S
5 U l [& R( R+ U R$ 5 ( d [& R, " U R$ 5 [& R( R/ U R$ S 5 n
[& R( R+ U
5 ( d U R1 U R$ 5 [3 S 5 n U R5 U5 S
S U l U R5 U5 U S U l g )Nr z3mode should be 'train', 'valid' or 'test', but got )pilcv2z4Expected backend are one of ['pil', 'cv2'], but got z>data_file is not set and downloading automatically is disabledflowersz?label_file is not set and downloading automatically is disabledz?setid_file is not set and downloading automatically is disabledz.tgz/jpgzscipy.iolabelsr ) lowerpaddlevisionget_image_backend
ValueErrorr
MODE_FLAG_MAPr DATA_URLDATA_MD5 LABEL_URL LABEL_MD5 SETID_URL SETID_MD5r# tarfileopenreplace data_pathospathexistsmkdirjoin
extractallr loadmatr* indexes) selfr r r r! r# downloadr flagdata_tarjpg_pathscios ^/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/vision/datasets/flowers.py__init__Flowers.__init__ s zz|
H A G H
? mm557G . ( FwiP
TZZ\*
P
8 38Xy(I
Q
8 4Iy)XJ
Q
8 4Iy)XJ #<< *"**637ww~~dnn-- HHT^^ $77<<6ww~~h'' /*%ll:.x8; ||J/5a8 c | U R U n[ R " U R US-
/5 nSUS S3n[ R
R
U R U5 nU R S:X a [ R " U5 nO:U R S:X a* [ R " [ R " U5 5 nU R b U R U5 nU R S:X a XSR S5 4$ UR [ R " 5 5 UR S5 4$ )N z
jpg/image_05z.jpgr% r& int64)rB nparrayr* r; r< r? r: r r r8 r# astyper, get_default_dtype)rC idxindexlabelimg_nameimages rI __getitem__Flowers.__getitem__ s S!$++eai012 bz. T^^X6 <<5 JJu%E
\\U
"HHUZZ ./E >> %NN5)E <<5 ,,w// /||F 4 4 67 g9NNNrL c , [ U R 5 $ )N)lenrB )rC s rI __len__Flowers.__len__ s 4<< rL )r r: rB r* r# )NNNr NTN)r r r r r r r! r r# r" rD boolr z_ImageBackend | NonereturnNone)rU intra z,tuple[_ImageDataType, npt.NDArray[np.int64]])
__name__
__module__ __qualname____firstlineno____doc____annotations__rJ rZ r^ __static_attributes__ rL rI r r 6 s @D
** !%!%!% $15 (,>9 >9 >9 >9
>9 /
>9 >9 &>9
>9@OO 5O(!rL r )r
znpt.NDArray[np.int64])%
__future__r typingr r r numpy.typingnpt#paddle.vision.transforms.transformsr rY r r
r r; r7 numpyrQ PILr r, paddle.dataset.commonr paddle.ior paddle.utilsr __all__r1 r3 r5 r2 r4 r6 r0 tupler rk rL rI rx s # . . >534L
< #
E G A - . .
"7WE
_!ge EFG _!rL