CocoCaptions

class torchvision.datasets.CocoCaptions(root: Union[str, Path], annFile: str, transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, transforms: Optional[Callable] = None)

MS Coco Captions 資料集。

它需要安裝 pycocotools，可以透過 pip install pycocotools 或 conda install conda-forge::pycocotools 進行安裝。

引數:

• root (str 或 pathlib.Path) – 用於下載影像的根目錄。

• annFile (string) – 註釋檔案（JSON格式）的路徑。

• transform (callable, optional) – 一個函式/變換，接收 PIL 影像並返回變換後的版本。例如，transforms.PILToTensor

• target_transform (可呼叫物件, 可選) – 一個函式/變換，接受目標並對其進行變換。

• transforms (callable, optional) – 接受輸入樣本及其目標並返回轉換後版本的函式/轉換。

示例

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)

輸出

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']

特殊成員:

__getitem__(index: int) → tuple[Any, Any]

引數:

index (int) – 索引

返回:

樣本和元資料，可透過相應的變換進行可選變換。

返回型別:

(Any)