EitSSKrSSKJr SSKJrJrJrJr SSK J r SSK J r "SS\ 5r "S S \ 5rg) N)Path)AnyCallableOptionalUnion)Image) VisionDatasetc ^\rSrSrSrSS\\\4S\S\\ S\\ S\\ S S4 U4S jjjr S \ S \ R4S jr S \ S \\4S jrS\ S \\\44SjrS \ 4SjrSrU=r$) CocoDetection a8`MS Coco Detection `_ Dataset. It requires `pycocotools `_ to be installed, which could be installed via ``pip install pycocotools`` or ``conda install conda-forge::pycocotools``. Args: root (str or ``pathlib.Path``): Root directory where images are downloaded to. annFile (string): Path to json annotation file. transform (callable, optional): A function/transform that takes in a PIL image and returns a transformed version. E.g, ``transforms.PILToTensor`` target_transform (callable, optional): A function/transform that takes in the target and transforms it. transforms (callable, optional): A function/transform that takes input sample and its target as entry and returns a transformed version. NrootannFile transformtarget_transform transformsreturnc>[TU]XX45 SSKJn U"U5Ul[ [ URRR555Ul g)Nr)COCO) super__init__pycocotools.cocorcocolistsortedimgskeysids)selfrrrrrr __class__s V/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/datasets/coco.pyrCocoDetection.__init__sD 9G)M tyy~~22456idcURRU5SSn[R"[R R URU55RS5$)Nr file_nameRGB) rloadImgsropenospathjoinrconvert)rr$r+s r! _load_imageCocoDetection._load_image)sMyy!!"%a(5zz"'',,tyy$78@@GGr#cjURRURRU55$N)rloadAnns getAnnIds)rr$s r! _load_targetCocoDetection._load_target-s&yy!!$))"5"5b"9::r#indexc[U[5(d[S[U5S35eURUnUR U5nUR U5nURbURX45up4X44$)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr.r4r)rr6r$imagetargets r! __getitem__CocoDetection.__getitem__0sw%%%B4;-yYZ Z XXe_  $""2& ?? & OOE:ME}r#c,[UR5$r1)lenr)rs r!__len__CocoDetection.__len__>s488}r#)rr)NNN)__name__ __module__ __qualname____firstlineno____doc__rstrrrrrr9rr.rrr4tupler>rB__static_attributes__ __classcell__r s@r!r r s()-/3)- 7CI 7 7H% 7 #8, 7 X& 7  7 7HcHekkH;s;tCy;  sCx r#r c>^\rSrSrSrS\S\\4U4SjjrSr U=r $) CocoCaptionsBa`MS Coco Captions `_ Dataset. It requires `pycocotools `_ to be installed, which could be installed via ``pip install pycocotools`` or ``conda install conda-forge::pycocotools``. Args: root (str or ``pathlib.Path``): Root directory where images are downloaded to. annFile (string): Path to json annotation file. transform (callable, optional): A function/transform that takes in a PIL image and returns a transformed version. E.g, ``transforms.PILToTensor`` target_transform (callable, optional): A function/transform that takes in the target and transforms it. transforms (callable, optional): A function/transform that takes input sample and its target as entry and returns a transformed version. Example: .. code:: python import torchvision.datasets as dset import torchvision.transforms as transforms cap = dset.CocoCaptions(root = 'dir where images are', annFile = 'json annotation file', transform=transforms.PILToTensor()) print('Number of samples: ', len(cap)) img, target = cap[3] # load 4th sample print("Image Size: ", img.size()) print(target) Output: :: Number of samples: 82783 Image Size: (3L, 427L, 640L) [u'A plane emitting smoke stream flying over a mountain.', u'A plane darts across a bright blue sky behind a mountain covered in snow', u'A plane leaves a contrail above the snowy mountain top.', u'A mountain that has a plane flying overheard in the distance.', u'A mountain view with a plume of smoke in the background'] r$rcR>[TU]U5Vs/sHo"SPM sn$s snf)Ncaption)rr4)rr$annr s r!r4CocoCaptions._load_targetns)*/'*>r*BC*B3I*BCCCs$) rDrErFrGrHr9rrIr4rKrLrMs@r!rOrOBs))VDsDtCyDDr#rO)os.pathr*pathlibrtypingrrrrPILrvisionr r rOrUr#r!r[s211!5M5p-D=-Dr#