Args: dataset_name (str): name of the dataset, e.g., "voc_2007_test"

Args: dataset_name (str): name of the dataset to be evaluated. It must have either the following corresponding me

Similar to `build_detection_train_loader`. But this function uses the given `dataset_name` argument (instead of the names in cfg), and us

A data loader is created by the following steps: 1. Use the dataset names in config to query :class:`DatasetCatalog`, and obtain a list of di

Build a LR scheduler from config.

Build a LR scheduler from config.

Build an optimizer from config.

Returns: torch.optim.Optimizer: It now calls :func:`detectron2.solver.build_optimizer`. Overwrite it if you'd lik

Returns: torch.optim.Optimizer: It now calls :func:`detectron2.solver.build_optimizer`. Overwrite it if you'd lik

Returns: iterable It calls :func:`detectron2.data.build_detection_train_loader` with a customized DatasetMapper,

Returns: iterable It calls :func:`detectron2.data.build_detection_train_loader` with a customized DatasetMapper,

Returns: dict: has a key "segm", whose value is a dict of "AP", "AP50", and "AP75".

Returns: dict: has a key "segm", whose value is a dict of "AP", "AP50", and "AP75".

Args: features (list[Tensor]): list of feature maps Returns: list[Tensor]: A list of L elements.

Args: images (ImageList): input images of length `N` features (dict[str, Tensor]): input data as a mapping from featu

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper` . Each item in the list contains the inpu

See :meth:`ROIHeads.forward`.

Args: features (list[Tensor]): list of feature maps Returns: list[Tensor]: A list of L elements.

Args: images (ImageList): input images of length `N` features (dict[str, Tensor]): input data as a mapping from featu

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper` . Each item in the list contains the inpu

See :meth:`ROIHeads.forward`.

Get a copy of the default config. Returns: a detectron2 CfgNode instance.

Deprecated

Returns: list[Instances]: same as `fsod_fast_rcnn_inference`. list[Tensor]: same as `fsod_fast_rcnn_inference`.

Deprecated

Returns: list[Instances]: same as `fsod_fast_rcnn_inference`. list[Tensor]: same as `fsod_fast_rcnn_inference`.

Args: predictions: return values of :meth:`forward()`. proposals (list[Instances]): proposals that match the features

Args: predictions: return values of :meth:`forward()`. proposals (list[Instances]): proposals that match the features

Performs non-maximum suppression on a boxlist, with scores specified in a boxlist field via score_field. Args: boxlist (dete

Performs non-maximum suppression on a boxlist, with scores specified in a boxlist field via score_field. Args: boxlist (dete

Returns: list[Tensor]: A list of Tensors of predicted boxes for GT classes in case of class-specific box head. El

Returns: list[Tensor]: A list of Tensors of predicted boxes for GT classes in case of class-specific box head. El

Args: inputs: the inputs to a COCO model (e.g., GeneralizedRCNN). It is a list of dict. Each dict corresponds to

Args: inputs: the inputs to a COCO model (e.g., GeneralizedRCNN). It is a list of dict. Each dict corresponds to