+ jv^RIt^RIHt^RIHtHtHtHt^RI H t ^RI H t !RR] 4t !RR ] 4tR#) N)Path)AnyCallableOptionalUnion)Image) VisionDatasetcaa]tRt^ toRtR V3RlV3RllltV3RlRltV3RlRltV3RlR ltV3R lR lt R t Vt V;t #) CocoDetectiona8`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. c <V^8dQhRS[S[S[3,RS[RS[S[,RS[S[,RS[S[,RR/#)rootannFile transformtarget_transform transformsreturnN)rstrrrr)format __classdict__s"Z/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/datasets/coco.py __annotate__CocoDetection.__annotate__s_ 7 7CI 7 7H% 7 #8, 7 X& 7  7c<\SV`WW44^RIHpV!V4Vn\ \ VPPP444Vn R#)r)COCON) super__init__pycocotools.cocorcocolistsortedimgskeysids)selfrrrrrr __class__s&&&&&& rrCocoDetection.__init__sD 9G)M tyy~~22456rc:<V^8dQhRS[RS[P/#r idr)intr)rrs"rrr)s#HHcHekkHrcVPPV4^,R,p\P!\P P VPV44PR4#)r file_nameRGB) r loadImgsropenospathjoinrconvert)r&r+r3s&& r _load_imageCocoDetection._load_image)sMyy!!"%a(5zz"'',,tyy$78@@GGrc6<V^8dQhRS[RS[S[,/#r*)r,r!r)rrs"rrr-s;;s;tCy;rcjVPPVPPV44#N)r loadAnns getAnnIds)r&r+s&&r _load_targetCocoDetection._load_target-s&yy!!$))"5"5b"9::rc<<V^8dQhRS[RS[S[S[3,/#)r indexr)r,tupler)rrs"rrr0s#   sCx rc\V\4'g\R\V4 R24hVPV,pVP V4pVP V4pVPeVPW44wr4W43#)z#Index must be of type integer, got z instead.) isinstancer, ValueErrortyper%r6r=r)r&r@r+imagetargets&& r __getitem__CocoDetection.__getitem__0sw%%%B4;-yYZ Z XXe_  $""2& ?? & OOE:ME}rc <V^8dQhRS[/#)r r)r,)rrs"rrr>src,\VP4#r:)lenr%)r&s&r__len__CocoDetection.__len__>s488}r)r r%)NNN) __name__ __module__ __qualname____firstlineno____doc__rr6r=rHrM__static_attributes____classdictcell__ __classcell__r'rs@@rr r sC 7 7HH;;  rr cBaa]tRt^BtoRtV3RlV3RlltRtVtV;t#) CocoCaptionsa`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'] c6<V^8dQhRS[RS[S[,/#r*)r,r!r)rrs"rrCocoCaptions.__annotate__ns#DDsDtCyDrcX<\SV`V4Uu.uF q"R,NK up#uupi)caption)rr=)r&r+annr's&& rr=CocoCaptions._load_targetns+*/'*>r*BC*B3I*BCCCs') rOrPrQrRrSr=rTrUrVrWs@@rrYrYBs)VDDDrrY)os.pathr2pathlibrtypingrrrrPILrvisionr r rYr`rrrfs211!5M5p-D=-Dr