U hT@spddlZddlmZddlmZmZmZmZm Z m Z ddl m Z ddl mZGdddeZGd d d eZdS) N)Path)AnyCallableListOptionalTupleUnion)Image) VisionDatasetcseZdZdZdeeefeeeeeeeddfdd Z e e j dddZ e e edd d Ze eeefd d d Ze dddZZS) CocoDetectiona`MS Coco Detection `_ Dataset. It requires the `COCO API to be installed `_. 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. N)rootannFile transformtarget_transform transformsreturncsBt||||ddlm}|||_tt|jj|_ dS)Nr)COCO) super__init__Zpycocotools.cocorcocolistsortedZimgskeysids)selfr rrrrr __class__K/var/www/html/venv/lib/python3.8/site-packages/torchvision/datasets/coco.pyrs  zCocoDetection.__init__idrcCs0|j|dd}ttj|j|dS)Nr file_nameRGB) rZloadImgsr openospathjoinr convert)rr!r&rrr _load_image(szCocoDetection._load_imagecCs|j|j|SN)rZloadAnnsZ getAnnIdsrr!rrr _load_target,szCocoDetection._load_target)indexrcCs^t|tstdt|d|j|}||}||}|jdk rV|||\}}||fS)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr)r,r)rr-r!imagetargetrrr __getitem__/s     zCocoDetection.__getitem__)rcCs t|jSr*)lenr)rrrr__len__=szCocoDetection.__len__)NNN)__name__ __module__ __qualname____doc__rstrrrrrr/r r)rrr,rr4r6 __classcell__rrrrr s  r cs,eZdZdZeeedfdd ZZS) CocoCaptionsa`MS Coco Captions `_ Dataset. It requires the `COCO API to be installed `_. 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 csddt|DS)NcSsg|] }|dqS)captionr).0annrrr msz-CocoCaptions._load_target..)rr,r+rrrr,lszCocoCaptions._load_target) r7r8r9r:r/rr;r,r<rrrrr=As*r=)os.pathr%pathlibrtypingrrrrrrZPILr Zvisionr r r=rrrrs     7