Async test without augmentation.

Test det bboxes with test time augmentation, can be applied in DenseHead except for ``RPNHead`` and its variants, e.g., ``GARPNHead``,

Test with augmentations.

Test with augmentations.

Test with augmentations. If rescale is False, then returned bboxes and masks will fit the scale of imgs[0].

Test function with test time augmentation.

Test function with test time augmentation. Args: imgs (list[Tensor]): the outer list indicates test-time augmenta

Test function with test time augmentation.

Backward function.

Flip bboxes horizontally or vertically. Args: bboxes(ndarray): shape (..., 5*k) img_shape(tuple): (height, width)

Bhatacharyya distance loss. Args: pred (torch.Tensor): Predicted bboxes. target (torch.Tensor): Corresponding gt bboxes.

Build RoI operator to extract feature from each level feature map. Args: layer_cfg (dict): Dictionary to construct and config RoI

calculate the training time.

Check whether the `pipeline_results` is the same with the predefined `results`. Args: results (dict): Predefined results which should

The custom accuracy.

The custom accuracy.

The custom activation.

The custom activation.

The custom cls channels.

The custom cls channels.

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 5) or (N, 5) pr

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 4) or (N, 4) pr

Apply transformation `fix_deltas` to `boxes`. Args: hbboxes (torch.Tensor): Basic boxes. Shape (B, N, 4) or (N, 4) fi

Apply transformation `fix_deltas` to `boxes`. Args: bboxes (torch.Tensor) bboxes_pred (torch.Tensor) Returns

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). pred_bboxes (Tensor): D

Apply transformation `pred_bboxes` to `bboxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 4) or (N, 4) p

The dynamic top k selection of point set samples based on the quality assessment values. Args: quality (torch.tensor): th

Get box regression transformation deltas that can be used to transform the ``bboxes`` into the ``gt_bboxes``. Args: bboxe

Get box regression transformation deltas that can be used to transform the ``bboxes`` into the ``gt_bboxes``. Args: bboxe

Get box regression transformation deltas. Args: rbboxes (torch.Tensor): Source boxes, e.g., object proposals. Returns:

Get box regression transformation deltas. Args: rbboxes (torch.Tensor): Source boxes, e.g., object proposals. Returns:

Encode bounding box to distances. Args: points (Tensor): Shape (N, 2), The format is [x, y]. gt_bboxes (Tensor): Shap

Get box regression transformation deltas that can be used to transform the ``bboxes`` into the ``gt_bboxes``. Args: bboxe

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate output shape.

Evaluate output shape.

Format the results to submission text (standard format for DOTA evaluation). Args: results (list): Testing results of the

Format the results to submission text (standard format for DOTA evaluation). Args: results (list): Testing results of the

Forward function of ConvModule.

Forward function of ReFPN.

Forward function of BasicBlock.

Forward function of Bottleneck.

Forward function of ReResNet.

Forward function.

Forward function.

Forward features from the upstream network. Args: feats (tuple[Tensor]): Features from the upstream network, each is

Forward function.

Forward function.

Forward function.

Forward function.

Forward function.

Forward function. Args: feats (torch.Tensor): Input features. rois (torch.Tensor): Input RoIs, shape (k, 5).

Forward function of Rotated BBoxHead.

Forward function.

Forward function.

Forward function.

Forward function of AlignConv.

Args: x (list[Tensor]): feature maps of multiple scales best_rbboxes (list[list[Tensor]]):

Args: x (list[Tensor]): feature maps of multiple scales best_rbboxes (list[list[Tensor]]):

Forward function. Args: ctx: {save_for_backward, convex_points_grad} pred (torch.Tensor): Predicted convexes.

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Forward function. Args: ctx: {save_for_backward, convex_points_grad} pred (torch.Tensor): Predicted convexes.

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Forward function. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the predic

Forward function. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning label of the predict

Forward function. Args: pred (torch.Tensor): Predicted convexes. target (torch.Tensor): Corresponding gt convexes.

Dummy forward function. Args: x (list[Tensors]): list of multi-level img features. proposals (list[Tensors]): list of

Dummy forward function. Args: x (list[Tensors]): list of multi-level img features. proposals (list[Tensors]): list of

Dummy forward function. Args: x (list[Tensors]): list of multi-level img features. proposals (list[Tensors]): list of

Dummy forward function. Args: x (list[Tensors]): list of multi-level img features. proposals (list[Tensors]): list of

Used for computing network flops. See `mmrotate/tools/analysis_tools/get_flops.py`

Used for computing network flops. See `mmrotate/tools/analysis_tools/get_flops.py`