DitddlZddlmZddlmZmZmZmZddl m Z ddl m Z Gdde Z Gd d e Zy) N)Path)AnyCallableOptionalUnion)Image) VisionDatasetc eZdZdZ ddeeefdedeedeedeeddf fd Z d e de jfd Z d e de efd Zd e deeeffdZde fdZxZS) CocoDetectionah`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 transformsreturnct|||||ddlm}|||_t t |jjj|_ y)Nr)COCO) super__init__pycocotools.cocorcocolistsortedimgskeysids)selfr rrrrr __class__s [/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/torchvision/datasets/coco.pyrzCocoDetection.__init__sI z96FG)M tyy~~22456idc|jj|dd}tjtj j |j|jdS)Nr file_nameRGB) rloadImgsropenospathjoinr convert)rr"r)s r _load_imagezCocoDetection._load_image)sMyy!!"%a(5zz"'',,tyy$78@@GGr!cj|jj|jj|SN)rloadAnns getAnnIds)rr"s r _load_targetzCocoDetection._load_target-s&yy!!$))"5"5b"9::r!indexct|tstdt|d|j|}|j |}|j |}|j|j||\}}||fS)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr,r1r)rr2r"imagetargets r __getitem__zCocoDetection.__getitem__0sz%%B4;-yYZ Z XXe_  $""2& ?? & OOE6:ME6f}r!c,t|jSr.)lenr)rs r __len__zCocoDetection.__len__>s488}r!)NNN)__name__ __module__ __qualname____doc__rstrrrrrr5rr,rrr1tupler:r= __classcell__rs@r r r s()-/3)- 7CI 7 7H% 7 #8, 7 X& 7  7HcHekkH;s;tCy;  sCx r!r c2eZdZdZdedeeffd ZxZS) 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'] r"rcNt||Dcgc]}|d c}Scc}w)Ncaption)rr1)rr"annrs r r1zCocoCaptions._load_targetns%*/'*>r*BC3ICCCs ") r>r?r@rAr5rrBr1rDrEs@r rGrGBs))VDsDtCyDDr!rG)os.pathr(pathlibrtypingrrrrPILrvisionr r rGr!r rQs211!5M5p-D=-Dr!