Ei9 n S SK Jr S SKJrJrJrJr SSKJr SSK J
r
J r J r J
r
SSKJr " S S\5 rg )
)Path)AnyCallableOptionalUnion )default_loader)check_integrity download_and_extract_archive download_urlverify_str_arg)
VisionDatasetc ^ \ rS rSrSrSrSSSS.rSS S
S .rS S
S
S\4S\ \
\ 4 S\
S\ \
S\ \
S\S\
\ \
\ 4 /\4 SS
4U 4S jjjrS\4S jrS\S\\\4 4S jrS\
4S jrS rS r/ S QrS rU =r$ )
Flowers102
a `Oxford 102 Flower `_ Dataset.
.. warning::
This class needs `scipy `_ to load target files from `.mat` format.
Oxford 102 Flower is an image classification dataset consisting of 102 flower categories. The
flowers were chosen to be flowers commonly occurring in the United Kingdom. Each class consists of
between 40 and 258 images.
The images have large scale, pose and light variations. In addition, there are categories that
have large variations within the category, and several very similar categories.
Args:
root (str or ``pathlib.Path``): Root directory of the dataset.
split (string, optional): The dataset split, supports ``"train"`` (default), ``"val"``, or ``"test"``.
transform (callable, optional): A function/transform that takes in a PIL image or torch.Tensor, depends on the given loader,
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the target and transforms it.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
loader (callable, optional): A function to load an image given its path.
By default, it uses PIL as its image loader, but users could also pass in
``torchvision.io.decode_image`` for decoding image data into tensors directly.
z2https://www.robots.ox.ac.uk/~vgg/data/flowers/102/)z102flowers.tgz 52808999861908f626f3c1f4e79d11fa)zimagelabels.mat e0620be6f572b9609742df49c70aed4d)z setid.mat a5357ecc9cb78c4bef273ce3793fc85c)imagelabelsetidtrnidvalidtstidtrainvaltestr NFrootsplit transformtarget_transformdownloadloaderreturnc $ > [ T
U ] XUS9 [ USS5 U l [ U R
5 S- U l U R S- U l U( a U R 5 U R 5 ( d [ S5 eSSK J n U" U R U R S S - S
S 9nXR U R R 5 n U" U R U R S S - S
S 9n
[! [# U
S
S-
R 5 S5 5 n / U l / U l U HM n U R$ R) X 5 U R& R) U R SU S S3- 5 MO X`l g )N)r! r" r r z flowers-102jpgzHDataset not found or corrupted. You can use download=True to download itr )loadmatr T)
squeeze_mer labelsr image_05dz.jpg)super__init__r
_splitr r _base_folder_images_folderr# _check_integrity RuntimeErrorscipy.ior(
_file_dict _splits_maptolistdict enumerate_labels _image_filesappendr$ )selfr r r! r" r# r$ r( set_ids image_idsr* image_id_to_labelimage_id __class__s \/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/datasets/flowers102.pyr. Flowers102.__init__. sm EUV$UG5MN Om ; " / /% 7 MMO$$&& ij j$$++doog.Fq.IIVZ[ , ,T[[ 9:AAC **T__W-Ea-HHUYZ F8,QU;V%V W " c , [ U R 5 $ N)lenr; r= s rC __len__Flowers102.__len__R s 4$$%%rE idxc U R U U R U p2U R U5 nU R ( a U R U5 nU R ( a U R U5 nXC4$ rG )r; r: r$ r! r" )r= rL
image_filer r s rC __getitem__Flowers102.__getitem__U sa - -c 2DLL4EE J' >>NN5)E ))%0E|rE c SU R 3$ )Nzsplit=)r/ rI s rC
extra_reprFlowers102.extra_repra s }%%rE c U R R 5 ( a U R R 5 ( d gS H= nU R U u p#[ [ U R U- 5 U5 ( a M= g g)NFr r T)r1 existsis_dirr5 r
strr0 r= idfilenamemd5s rC r2 Flowers102._check_integrityd sm ##**,,1D1D1K1K1M1M$B OOB /MH"3t'8'88'C#DcJJ % rE c R U R 5 ( a g [ U R U R S S 3[ U R
5 U R S S S9 S H? nU R U u p#[
U R U- [ U R
5 US9 MA g )Nr r r )r\ rU )r2 r _download_url_prefixr5 rX r0 r rY s rC r# Flowers102.downloadn s " " $(()$//'*B1*E)F G !! "(+
%B OOB /MH 22X=s4CTCT?U[^ _ %rE )fz
pink primrosezhard-leaved pocket orchidzcanterbury bellsz sweet peazenglish marigoldz
tiger lilyz moon orchidzbird of paradise monkshoodz
globe thistle
snapdragonz colt's footz king proteaz
spear thistlez yellow irisz globe-flowerzpurple coneflowerz
peruvian lilyzballoon flowerzgiant white arum lilyz fire lilyzpincushion flower
fritillaryz
red gingerzgrape hyacinthz
corn poppyzprince of wales featherszstemless gentian artichokez
sweet william carnationz garden phloxzlove in the mistz
mexican asterzalpine sea hollyzruby-lipped cattleyaz cape flowerzgreat masterwortz
siam tulipz lenten rosezbarbeton daisydaffodilz
sword lily
poinsettiazbolero deep blue
wallflowermarigold buttercupz oxeye daisyzcommon dandelionpetuniaz
wild pansyprimula sunflower pelargoniumzbishop of llandaffgaurageraniumz
orange dahliazpink-yellow dahlia?zcautleya spicatazjapanese anemonezblack-eyed susan
silverbushzcalifornian poppy osteospermumz
spring crocusz bearded iris
windflowerz
tree poppygazaniaazaleaz
water lilyrosez thorn applez
morning gloryzpassion flowerlotusz toad lily anthurium
frangipaniclematishibiscus columbinez desert-rosez tree mallowmagnoliacyclamen
watercressz
canna lily hippeastrumzbee balmz ball mossfoxglove
bougainvilleacamelliamallowzmexican petuniabromeliazblanket flowerztrumpet creeperzblackberry lily)r0 r; r1 r: r/ r$ )__name__
__module__ __qualname____firstlineno____doc__r_ r5 r6 r r rX r r r boolr r. intrJ tuplerO rR r2 r# classes__static_attributes__
__classcell__)rB s @rC r r
s 6 PGHBJ
$GWEK
(,/3 4B" CI " " H% "
#8, "
" %T *+S01"
" " H& &
s
uS#X
&C &
`gGrE r N)pathlibr typingr r r r folderr utilsr
r r r
visionr r rE rC r s( 1 1 " ^ ^ !W WrE