+
j x ^ RI t ^ RIt^ RIHtHtHtHt ^ RIHt ^RI H
t
^RI H t H
t
^RIHt ! R R]4 tR# ) N)AnyCallableOptionalUnion)urlparse)default_loader) download_and_extract_archiveverify_str_arg)
VisionDatasetc a a ] tR t^ t oRtRtRtRRRR]3V3R lV 3R llltV3R lR
lt V3R lR lt
V3R
lR lt V3R lR lt V3R lR lt
RtVtV ;t# )CLEVRClassificationax `CLEVR `_ classification dataset.
The number of objects in a scene are used as label.
Args:
root (str or ``pathlib.Path``): Root directory of dataset where directory ``root/clevr`` exists or will be saved to if download is
set to True.
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 them 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.
z3https://dl.fbaipublicfiles.com/clevr/CLEVR_v1.0.zip b11922020e72d0cd9154779b2d3d07d2trainNFc < V ^8 d QhRS[ S[S[P 3, RS[RS[S[, RS[S[, RS[RS[S[ S[S[P 3, .S[3, RR/# ) rootsplit transformtarget_transformdownloadloaderreturnN)r strpathlibPathr r boolr )format
__classdict__s "[/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/datasets/clevr.py __annotate__ CLEVRClassification.__annotate__" s ; ;C %& ; ; H% ;
#8, ;
; %W\\ 123S89 ;
; c h < \ VR R
4 V n \ S V `
WVR7 W`n \
P ! V P 4 R, V n V P \
P ! \ V P 4 P 4 P , V n
V' d V P 4 V P 4 ' g \! R4 h\# V P P% RV P 4 P' R4 4 V n V V P R8w d \+ V P R, RV P R 2, 4 ;_uu_ 4 p\, P. ! V4 pR
R
R
4 XR, U u/ uF qR , \1 V R , 4 bK p
p V P( U u. uF qV P2 , NK up V n R
# R
.\1 V P( 4 , V n R
# + ' g i L; iu up i u up i )r test)r r clevrzHDataset not found or corrupted. You can use download=True to download itimages*scenesCLEVR_z _scenes.jsonNimage_filenameobjects)r valr$ )r
_splitsuper__init__r r r r _base_folderr _URLpathstem _data_folder _download
_check_exists RuntimeErrorsortedjoinpathglob _image_filesopenjsonloadlenname_labels)
selfr r r r r r filecontentscene num_objects
image_file __class__s
&&&&&&& r r/ CLEVRClassification.__init__" s %UG5MN
EUV #LL 3g = - - Xdii=P=U=U0V0[0[ [ NN !!## ij j "4#4#4#=#=h #T#Y#YZ]#^ _ ;;& d''(2vdkk],5WWXX\` ))D/ YW^_gWhiWhe!12Ci8H4IIWhKiKOK\K\]K\Z
8 8K\]DL 6C(9(9$::DL YXi]s 2H "H*H/ H' c < V ^8 d QhRS[ /# r r )int)r r s "r r r! B s & & &r" c , \ V P 4 # N)r? r; rB s &r __len__CLEVRClassification.__len__B s 4$$%%r" c < < V ^8 d QhRS[ RS[S[S[3, /# )r idxr )rL tupler )r r s "r r r! E s# s uS#X r" c V P V, pV P V, pV P V4 pV P ' d V P V4 pV P ' d V P V4 pWC3# rN )r; rA r r r )rB rS rG labelimages && r __getitem__ CLEVRClassification.__getitem__E si &&s+
S! J' >>>NN5)E ))%0E|r" c < V ^8 d QhRS[ /# rK )r )r r s "r r r! S s I It Ir" c z V P P 4 ;' d V P P 4 # rN )r4 existsis_dirrO s &r r6 !CLEVRClassification._check_existsS s. '')HHd.?.?.F.F.HHr" c < V ^8 d QhRR/# )r r N )r r s "r r r! V s W W4 Wr" c V P 4 ' d R # \ V P \ V P 4 V P
R7 R # )N)md5)r6 r r1 r r0 _MD5rO s &r r5 CLEVRClassification._downloadV s3 $TYYD4E4E0FDIIVr" c < V ^8 d QhRS[ /# rK )r )r r s "r r r! \ s & &C &r" c R V P 2# )zsplit=)r- rO s &r
extra_repr CLEVRClassification.extra_repr\ s }%%r" )r0 r4 r; rA r- r )__name__
__module__ __qualname____firstlineno____doc__r1 rc r r/ rP rX r6 r5 rg __static_attributes____classdictcell__
__classcell__)rH r s @@r r
r
sn $ AD -D
(,/3 rv s+ 1 1 ! " ? !Q&- Q&r"