ObjectDetectionImageDataset#

class ObjectDetectionImageDataset[source]#

Bases: ImageDataset

Read Object Detection data in the COCO format.

Uses CocoDataset to read the data.

__init__(img_dir: str, annotation_uri: str, *args, **kwargs)[source]#

Constructor.

Parameters
  • img_dir (str) – Directory containing the images. Image filenames must match the image IDs in the annotations file.

  • annotation_uri (str) – URI to a JSON file containing annotations in the COCO format.

  • *args – See ImageDataset.__init__().

  • **kwargs – See ImageDataset.__init__().

Methods

__init__(img_dir, annotation_uri, *args, ...)

Constructor.

__contains__(key: str) bool#
Parameters

key (str) –

Return type

bool

__getitem__(key) Tuple[torch.Tensor, torch.Tensor]#
Return type

Tuple[torch.Tensor, torch.Tensor]

__init__(img_dir: str, annotation_uri: str, *args, **kwargs)[source]#

Constructor.

Parameters
  • img_dir (str) – Directory containing the images. Image filenames must match the image IDs in the annotations file.

  • annotation_uri (str) – URI to a JSON file containing annotations in the COCO format.

  • *args – See ImageDataset.__init__().

  • **kwargs – See ImageDataset.__init__().

static __new__(cls, *args: Any, **kwargs: Any) Any#
Parameters
  • args (Any) –

  • kwargs (Any) –

Return type

Any