Rearrange the tensor layout from the network output, i.e.: list[Tensor]: #lvl tensors of shape (N, A x K, Hi, Wi) to per-image prediction

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta, box_center: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta, box_center: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` anchors (list[list[Boxes]]): a list of

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]): a list of #

Arguments: box_cls, box_delta, box_filter: Same as the output of :meth:`FCOSHead.forward` shifts (list[list[Tensor]):

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Normalize, pad and batch the input images.

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: anchors (list[list[Boxes]]): a list of N=#image elements. Each is a list of #feature level Boxes. The Boxes

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

Args: shifts (list[list[Tensor]]): a list of N=#image elements. Each is a list of #feature level tensors. The ten

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh

Args: For `gt_classes`, `gt_shifts_deltas` and `gt_centerness` parameters, see :meth:`FCOS.get_ground_truth`.

Args: For `gt_classes`, `gt_shifts_deltas` and `gt_centerness` parameters, see :meth:`FCOS.get_ground_truth`.

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh

Args: For `gt_classes` and `gt_anchors_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their s

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh

Args: For `gt_classes` and `gt_shifts_deltas` parameters, see :meth:`FCOS.get_ground_truth`. Their sh