jddlZddlmZddlmZmZmZmZm Z m Z ddl m Z ddl mZGddeZGd d eZdS) N)Path)AnyCallableListOptionalTupleUnion)Image) VisionDatasetc eZdZdZ ddeeefdedeedeedeeddf fd Z d e de j fd Z d e de efd Zd e deeeffdZde fdZxZS) 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. NrootannFile transformtarget_transform transformsreturnct||||ddlm}|||_t t |jj|_ dS)Nr)COCO) super__init__pycocotools.cocorcocolistsortedimgskeysids)selfrrrrrr __class__s JC:\Projects\Historical\venv\Lib\site-packages\torchvision/datasets/coco.pyrzCocoDetection.__init__sp z96FGGG))))))DMM ty~22445566idc|j|dd}tjtj|j|dS)Nr file_nameRGB) rloadImgsr openospathjoinrconvert)r r$r+s r" _load_imagezCocoDetection._load_image(sQy!!"%%a(5z"',,ty$7788@@GGGr#cf|j|j|SN)rloadAnns getAnnIds)r r$s r" _load_targetzCocoDetection._load_target,s(y!!$)"5"5b"9"9:::r#indexc"t|ts tdt|d|j|}||}||}|j|||\}}||fS)Nz#Index must be of type integer, got z instead.) isinstanceint ValueErrortyperr.r3r)r r4r$imagetargets r" __getitem__zCocoDetection.__getitem__/s%%% [Y4;;YYYZZ Z Xe_  $$""2&& ? & OOE6::ME6f}r#c*t|jSr0)lenr)r s r"__len__zCocoDetection.__len__=s48}}r#)NNN)__name__ __module__ __qualname____doc__r strrrrrr7r r.rrr3rr<r? __classcell__r!s@r"rr s>  &)-/3)- 7 7CI 7 7H% 7 #8, 7 X& 7  7 7 7 7 7 7HcHekHHHH;s;tCy;;;;  sCx    r#rc8eZdZdZdedeeffd ZxZS) 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$rcZdt|DS)Ncg|] }|d S)caption).0anns r" z-CocoCaptions._load_target..msCCC3ICCCr#)rr3)r r$r!s r"r3zCocoCaptions._load_targetls)CC%''*>*>r*B*BCCCCr#) r@rArBrCr7rrDr3rErFs@r"rHrHAsf((TDsDtCyDDDDDDDDDDr#rH)os.pathr*pathlibrtypingrrrrrr PILr visionr rrHrLr#r"rUs>>>>>>>>>>>>>>>>!!!!!!44444M444n,D,D,D,D,D=,D,D,D,D,Dr#