Prepare some proposals to be used to train the ROI heads. It performs box matching between `proposals` and `targets`, and assigns

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 an optimizer from config.

Call `fsod_fast_rcnn_inference_single_image` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-specif

Call `fsod_fast_rcnn_inference_single_image` for all images. Args: boxes (list[Tensor]): A list of Tensors of predicted class-specif

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

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_ins

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_ins

Return the losses from a set of RPN predictions and their associated ground-truth. Args: anchors (list[Boxes or RotatedB

Return the losses from a set of RPN predictions and their associated ground-truth. Args: anchors (list[Boxes or RotatedB

Decode all the predicted box regression deltas to proposals. Find the top proposals by applying NMS and removing boxes that are too s

Decode all the predicted box regression deltas to proposals. Find the top proposals by applying NMS and removing boxes that are too s

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

NOTE: this interface is experimental. Args: in_features (list[str]): list of names of input features to use

Args: box2box_transform (Box2BoxTransform/Box2BoxTransformRotated): box2box transform instance for proposal-to-de

NOTE: this interface is experimental. Args: in_features (list[str]): list of names of input features to use

Args: box2box_transform (Box2BoxTransform/Box2BoxTransformRotated): box2box transform instance for proposal-to-de

Creates gradient clipping closure to clip by value or by norm, according to the provided config.

Creates gradient clipping closure to clip by value or by norm, according to the provided config.

Transform anchors into proposals by applying the predicted anchor deltas. Returns: proposals (list[Tensor]): A list of L

Transform anchors into proposals by applying the predicted anchor deltas. Returns: proposals (list[Tensor]): A list of L

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predic

Evaluate the box proposals in predictions. Fill self._results with the metrics for "box_proposals" task.

Evaluate the box proposals in predictions. Fill self._results with the metrics for "box_proposals" task.

Evaluate predictions on the given tasks. Fill self._results with the metrics of the tasks.

Evaluate predictions on the given tasks. Fill self._results with the metrics of the tasks.

Evaluate detection proposal recall metrics. This function is a much faster alternative to the official COCO API recall evaluation code. Howev

Evaluate detection proposal recall metrics. This function is a much faster alternative to the official COCO API recall evaluation code. Howev

Evaluate the coco results using COCOEval API.

Evaluate the coco results using COCOEval API.

Dynamically creates a new type that inherits the type of a given instance and overrides the `step` method to add gradient clipping

Dynamically creates a new type that inherits the type of a given instance and overrides the `step` method to add gradient clipping

Log the accuracy metrics to EventStorage.

Log the accuracy metrics to EventStorage.

Rescale the output instances to the target size.

Rescale the output instances to the target size.

Returns: Tensor: A Tensors of predicted class-specific or class-agnostic boxes for all images in a batch. Element

Returns: Tensor: A Tensors of predicted class-specific or class-agnostic boxes for all images in a batch. Element

Randomly sample a subset of positive and negative examples, and overwrite the label vector to the ignore value (-1) for all elements

Randomly sample a subset of positive and negative examples, and overwrite the label vector to the ignore value (-1) for all elements

Returns: tuple[str]: tasks that can be evaluated under the given configuration.

Returns: tuple[str]: tasks that can be evaluated under the given configuration.

Build ROIHeads defined by `cfg.MODEL.ROI_HEADS.NAME`.

Build ROIHeads defined by `cfg.MODEL.ROI_HEADS.NAME`.

Build an RPN head defined by `cfg.MODEL.RPN.HEAD_NAME`.

Build an RPN head defined by `cfg.MODEL.RPN.HEAD_NAME`.

Returns: iterable It now calls :func:`detectron2.data.build_detection_test_loader`. Overwrite it if you'd like a

Returns: iterable It now calls :func:`detectron2.data.build_detection_test_loader`. Overwrite it if you'd like a

See :meth:`ROIHeads.forward`.

See :meth:`ROIHeads.forward`.

Args: pred: Nx4 predicted bounding boxes target: Nx4 target bounding boxes weight: N loss weight for each

Args: pred: Nx4 predicted bounding boxes target: Nx4 target bounding boxes weight: N loss weight for each

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. Args: features: same as in `forward()`

Use the given boxes in `instances` to produce other (non-box) per-ROI outputs. Args: features: same as in `forward()`

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). Args

Single-image inference. Return bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). Args