o V h@spddlZddlmZddlmZmZmZmZm Z m Z ddl m Z ddl mZGdddeZGd d d eZdS) N)Path)AnyCallableListOptionalTupleUnion)Image) VisionDatasetc seZdZdZ   ddeeefdedeedeedeeddf fd d Z d e de j fd d Z d e de efddZde deeeffddZde fddZZS) 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 transformsreturncsBt||||ddlm}|||_tt|jj|_ dS)Nr)COCO) super__init__pycocotools.cocorcocolistsortedimgskeysids)selfr rrrrr __class__M/var/www/vscode/kcb/lib/python3.10/site-packages/torchvision/datasets/coco.pyrs  zCocoDetection.__init__idcCs0|j|dd}ttj|j|dS)Nr file_nameRGB) rloadImgsr openospathjoinr convert)rr"r(r r r! _load_image)szCocoDetection._load_imagecCs|j|j|SN)rloadAnns getAnnIdsrr"r r r! _load_target-szCocoDetection._load_targetindexcCs^t|tstdt|d|j|}||}||}|jdur+|||\}}||fS)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr+r0r)rr1r"imagetargetr r r! __getitem__0s     zCocoDetection.__getitem__cCs t|jSr,)lenr)rr r r!__len__>s zCocoDetection.__len__)NNN)__name__ __module__ __qualname____doc__rstrrrrrr3r r+rrr0rr8r: __classcell__r r rr!r s, r cs.eZdZdZdedeeffdd ZZS) 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"rcsddt|DS)NcSsg|]}|dqS)captionr ).0annr r r! osz-CocoCaptions._load_target..)rr0r/rr r!r0nszCocoCaptions._load_target) r;r<r=r>r3rr?r0r@r r rr!rABs"+rA)os.pathr'pathlibrtypingrrrrrrPILr visionr r rAr r r r!s    8