+
j | ^ RI t^ RIHt ^ RIHtHtHtHt ^ RI t
^ RI H t ^RI
HtHtHt ^RIHt ! R R]4 tR# ) N)Path)AnyCallableOptionalUnion)Image)check_integrity download_urlverify_str_arg)
VisionDatasetc a a ] tR t^ t oRtR. ROR. ROR. RO/tRV3R lV 3R llltV3R lR ltV3R lR
ltV3R lR lt V3R
lR lt
V3R lR lt Rt Vt
V ;t# )SVHNaD `SVHN `_ Dataset.
Note: The SVHN dataset assigns the label `10` to the digit `0`. However, in this Dataset,
we assign the label `0` to the digit `0` to be compatible with PyTorch loss functions which
expect the class labels to be in the range `[0, C-1]`
.. warning::
This class needs `scipy `_ to load data from `.mat` format.
Args:
root (str or ``pathlib.Path``): Root directory of the dataset where the data is stored.
split (string): One of {'train', 'test', 'extra'}.
Accordingly dataset is selected. 'extra' is Extra training set.
transform (callable, optional): A function/transform that takes in a PIL image
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.
traintestextrac r < V ^8 d QhRS[ S[S[3, RS[RS[S[, RS[S[, RS[RR/# ) rootsplit transformtarget_transformdownloadreturnN)r strr r r bool)format
__classdict__s "Z/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/datasets/svhn.py __annotate__SVHN.__annotate__6 sZ &: &:CI &: &: H% &:
#8, &:
&:
&: c < \ SV ` WVR 7 \ VR\ V P P 4 4 4 V n V P V, ^ , V n V P V, ^, V n V P V, ^, V n V' d V P 4 V P 4 ' g \ R4 h^ RI
Hp VP \ P" P% V P& V P 4 4 pVR, V n VR, P+ \, P. 4 P1 4 V n \, P4 ! V P2 V P2 ^
8H ^ 4 \, P6 ! V P( R4 V n R# ))r r r zHDataset not found or corrupted. You can use download=True to download itNXy) r r ) super__init__r tuple
split_listkeysr urlfilenamefile_md5r _check_integrity RuntimeErrorscipy.ioioloadmatospathjoinr dataastypenpint64squeezelabelsplace transpose) selfr r r r r sio
loaded_mat __class__s &&&&&& r r(
SVHN.__init__6 s1 EUV#E7E$//:N:N:P4QR
??5)!, .q1
.q1
MMO$$&& ij j [[ dii !GH
sO
!o,,RXX6>>@
dkkR /3LLL9 r! c < < V ^8 d QhRS[ RS[S[S[3, /# )r indexr )intr) r )r r s "r r r ^ s# sCx r! c 6 V P V, \ V P V, 4 r2\ P ! \
P ! VR4 4 pV P e V P V4 pV P e V P V4 pW#3# )zn
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
)r& r r ) r7 rF r< r fromarrayr9 r> r r )r? rE imgtargets && r __getitem__SVHN.__getitem__^ sy ii&DKK,>(?V oobll3 :; >> %..%C ,**62F{r! c < V ^8 d QhRS[ /# r r )rF )r r s "r r r t s r! c , \ V P 4 # )N)lenr7 r? s &r __len__ SVHN.__len__t s 499~ r! c < V ^8 d QhRS[ /# rN )r )r r s "r r r w s + +$ +r! c V P pV P V P , ^, p\ P P WP 4 p\ W24 # )r )r r* r r4 r5 r6 r- r )r? r md5fpaths & r r/ SVHN._check_integrityw sC yyoodjj)!, T==1 u**r! c < V ^8 d QhRR/# )r r N )r r s "r r r } s > >$ >r! c V P V P , ^, p\ V P V P V P
V4 R# )r N)r* r r
r, r r- )r? rV s & r r
SVHN.download} s3 oodjj)!,TXXtyy$--=r! c < V ^8 d QhRS[ /# rN )r )r r s "r r r s 8 8C 8r! c : R P ! R/ V P B # )zSplit: {split}rZ )r __dict__rQ s &r
extra_reprSVHN.extra_repr s &&7 77r! )r7 r. r- r< r r, )z6http://ufldl.stanford.edu/housenumbers/train_32x32.matztrain_32x32.mat e26dedcc434d2e4c54c9b2d4a06d8373)z5http://ufldl.stanford.edu/housenumbers/test_32x32.matztest_32x32.mat eb5a983be6a315427106f1b164d9cef3)z6http://ufldl.stanford.edu/housenumbers/extra_32x32.matzextra_32x32.mat a93ce644f1a588dc4d68dda5feec44a7)r NNF)__name__
__module__ __qualname____firstlineno____doc__r* r( rK rR r/ r r` __static_attributes____classdictcell__
__classcell__)rB r s @@r r r sq 0
J$&: &:P , + + > >8 8 8r! r )os.pathr4 pathlibr typingr r r r numpyr9 PILr utilsr r
r visionr r rZ r! r rt s. 1 1 @ @ !v8= v8r!