a h@shddlZddlmZddlmZmZmZmZddl m Z ddl m Z Gddde Z Gd d d e ZdS) N)Path)AnyCallableOptionalUnion)Image) VisionDatasetcseZdZdZdeeefeeeeeeeddfdd Z e e j dddZ e e edd d Ze eeefd d d Ze dddZZS) 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. N)rootannFile transformtarget_transform transformsreturncsBt||||ddlm}|||_tt|jj|_ dS)Nr)COCO) super__init__Zpycocotools.cocorcocolistsortedZimgskeysids)selfr r r rrr __class__G/var/www/auris/lib/python3.9/site-packages/torchvision/datasets/coco.pyrs  zCocoDetection.__init__idrcCs0|j|dd}ttj|j|dS)Nr file_nameZRGB) rZloadImgsropenospathjoinr convert)rrr#rrr _load_image)szCocoDetection._load_imagecCs|j|j|SN)rZloadAnnsZ getAnnIdsrrrrr _load_target-szCocoDetection._load_target)indexrcCs^t|tstdt|d|j|}||}||}|jdurV|||\}}||fS)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr&r)r)rr*rimagetargetrrr __getitem__0s     zCocoDetection.__getitem__)rcCs t|jSr')lenr)rrrr__len__>szCocoDetection.__len__)NNN)__name__ __module__ __qualname____doc__rstrrrrrr,rr&rrr)tupler1r3 __classcell__rrrrr s  r cs,eZdZdZeeedfdd 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'] rcsddt|DS)NcSsg|] }|dqS)captionr).0annrrr oz-CocoCaptions._load_target..)rr)r(rrrr)nszCocoCaptions._load_target) r4r5r6r7r,rr8r)r:rrrrr;Bs+r;)os.pathr"pathlibrtypingrrrrZPILrZvisionr r r;rrrrs    8