[Refactor] Refactor code structure and docstrings (#803)

* refactor points_in_boxes

* Merge same functions of three boxes

* More docstring fixes and unify x/y/z size

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Add "optional" and fix "Default"

* Remove None in function param type

* Fix unittest

* Add comments for NMS functions

* Merge methods of Points

* Add unittest

* Add optional and default value

* Fix box conversion and add unittest

* Fix comments

* Add unit test

* Indent

* Fix CI

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Remove useless \\

* Add unit test for box bev

* More unit tests and refine docstrings in box_np_ops

* Fix comment

* Add deprecation warning

mmdet3d/models/dense_heads/centerpoint_head.py

@@ -21,16 +21,16 @@ class SeparateHead(BaseModule):
     Args:
         in_channels (int): Input channels for conv_layer.
         heads (dict): Conv information.
-        head_conv (int): Output channels.
+        head_conv (int, optional): Output channels.
             Default: 64.
-        final_kernal (int): Kernal size for the last conv layer.
+        final_kernal (int, optional): Kernal size for the last conv layer.
             Deafult: 1.
-        init_bias (float): Initial bias. Default: -2.19.
-        conv_cfg (dict): Config of conv layer.
+        init_bias (float, optional): Initial bias. Default: -2.19.
+        conv_cfg (dict, optional): Config of conv layer.
             Default: dict(type='Conv2d')
-        norm_cfg (dict): Config of norm layer.
+        norm_cfg (dict, optional): Config of norm layer.
             Default: dict(type='BN2d').
-        bias (str): Type of bias. Default: 'auto'.
+        bias (str, optional): Type of bias. Default: 'auto'.
     """
 
     def __init__(self,
@@ -100,17 +100,17 @@ class SeparateHead(BaseModule):
         Returns:
             dict[str: torch.Tensor]: contains the following keys:
 
-                -reg （torch.Tensor): 2D regression value with the \
+                -reg （torch.Tensor): 2D regression value with the
                     shape of [B, 2, H, W].
-                -height (torch.Tensor): Height value with the \
+                -height (torch.Tensor): Height value with the
                     shape of [B, 1, H, W].
-                -dim (torch.Tensor): Size value with the shape \
+                -dim (torch.Tensor): Size value with the shape
                     of [B, 3, H, W].
-                -rot (torch.Tensor): Rotation value with the \
+                -rot (torch.Tensor): Rotation value with the
                     shape of [B, 2, H, W].
-                -vel (torch.Tensor): Velocity value with the \
+                -vel (torch.Tensor): Velocity value with the
                     shape of [B, 2, H, W].
-                -heatmap (torch.Tensor): Heatmap with the shape of \
+                -heatmap (torch.Tensor): Heatmap with the shape of
                     [B, N, H, W].
         """
         ret_dict = dict()
@@ -131,18 +131,19 @@ class DCNSeparateHead(BaseModule):
 
     Args:
         in_channels (int): Input channels for conv_layer.
+        num_cls (int): Number of classes.
         heads (dict): Conv information.
         dcn_config (dict): Config of dcn layer.
-        num_cls (int): Output channels.
+        head_conv (int, optional): Output channels.
             Default: 64.
-        final_kernal (int): Kernal size for the last conv layer.
-            Deafult: 1.
-        init_bias (float): Initial bias. Default: -2.19.
-        conv_cfg (dict): Config of conv layer.
+        final_kernal (int, optional): Kernal size for the last conv
+            layer. Deafult: 1.
+        init_bias (float, optional): Initial bias. Default: -2.19.
+        conv_cfg (dict, optional): Config of conv layer.
             Default: dict(type='Conv2d')
-        norm_cfg (dict): Config of norm layer.
+        norm_cfg (dict, optional): Config of norm layer.
             Default: dict(type='BN2d').
-        bias (str): Type of bias. Default: 'auto'.
+        bias (str, optional): Type of bias. Default: 'auto'.
     """  # noqa: W605
 
     def __init__(self,
@@ -215,17 +216,17 @@ class DCNSeparateHead(BaseModule):
         Returns:
             dict[str: torch.Tensor]: contains the following keys:
 
-                -reg （torch.Tensor): 2D regression value with the \
+                -reg （torch.Tensor): 2D regression value with the
                     shape of [B, 2, H, W].
-                -height (torch.Tensor): Height value with the \
+                -height (torch.Tensor): Height value with the
                     shape of [B, 1, H, W].
-                -dim (torch.Tensor): Size value with the shape \
+                -dim (torch.Tensor): Size value with the shape
                     of [B, 3, H, W].
-                -rot (torch.Tensor): Rotation value with the \
+                -rot (torch.Tensor): Rotation value with the
                     shape of [B, 2, H, W].
-                -vel (torch.Tensor): Velocity value with the \
+                -vel (torch.Tensor): Velocity value with the
                     shape of [B, 2, H, W].
-                -heatmap (torch.Tensor): Heatmap with the shape of \
+                -heatmap (torch.Tensor): Heatmap with the shape of
                     [B, N, H, W].
         """
         center_feat = self.feature_adapt_cls(x)
@@ -243,31 +244,30 @@ class CenterHead(BaseModule):
     """CenterHead for CenterPoint.
 
     Args:
-        mode (str): Mode of the head. Default: '3d'.
-        in_channels (list[int] | int): Channels of the input feature map.
-            Default: [128].
-        tasks (list[dict]): Task information including class number
+        in_channels (list[int] | int, optional): Channels of the input
+            feature map. Default: [128].
+        tasks (list[dict], optional): Task information including class number
             and class names. Default: None.
-        dataset (str): Name of the dataset. Default: 'nuscenes'.
-        weight (float): Weight for location loss. Default: 0.25.
-        code_weights (list[int]): Code weights for location loss. Default: [].
-        common_heads (dict): Conv information for common heads.
+        train_cfg (dict, optional): Train-time configs. Default: None.
+        test_cfg (dict, optional): Test-time configs. Default: None.
+        bbox_coder (dict, optional): Bbox coder configs. Default: None.
+        common_heads (dict, optional): Conv information for common heads.
             Default: dict().
-        loss_cls (dict): Config of classification loss function.
+        loss_cls (dict, optional): Config of classification loss function.
             Default: dict(type='GaussianFocalLoss', reduction='mean').
-        loss_bbox (dict): Config of regression loss function.
+        loss_bbox (dict, optional): Config of regression loss function.
             Default: dict(type='L1Loss', reduction='none').
-        separate_head (dict): Config of separate head. Default: dict(
+        separate_head (dict, optional): Config of separate head. Default: dict(
             type='SeparateHead', init_bias=-2.19, final_kernel=3)
-        share_conv_channel (int): Output channels for share_conv_layer.
-            Default: 64.
-        num_heatmap_convs (int): Number of conv layers for heatmap conv layer.
-            Default: 2.
-        conv_cfg (dict): Config of conv layer.
+        share_conv_channel (int, optional): Output channels for share_conv
+            layer. Default: 64.
+        num_heatmap_convs (int, optional): Number of conv layers for heatmap
+            conv layer. Default: 2.
+        conv_cfg (dict, optional): Config of conv layer.
             Default: dict(type='Conv2d')
-        norm_cfg (dict): Config of norm layer.
+        norm_cfg (dict, optional): Config of norm layer.
             Default: dict(type='BN2d').
-        bias (str): Type of bias. Default: 'auto'.
+        bias (str, optional): Type of bias. Default: 'auto'.
     """
 
     def __init__(self,
@@ -366,8 +366,8 @@ class CenterHead(BaseModule):
             feat (torch.tensor): Feature map with the shape of [B, H*W, 10].
             ind (torch.Tensor): Index of the ground truth boxes with the
                 shape of [B, max_obj].
-            mask (torch.Tensor): Mask of the feature map with the shape
-                of [B, max_obj]. Default: None.
+            mask (torch.Tensor, optional): Mask of the feature map with the
+                shape of [B, max_obj]. Default: None.
 
         Returns:
             torch.Tensor: Feature map after gathering with the shape
@@ -403,14 +403,14 @@ class CenterHead(BaseModule):
 
         Returns:
             Returns:
-                tuple[list[torch.Tensor]]: Tuple of target including \
+                tuple[list[torch.Tensor]]: Tuple of target including
                     the following results in order.
 
                     - list[torch.Tensor]: Heatmap scores.
                     - list[torch.Tensor]: Ground truth boxes.
-                    - list[torch.Tensor]: Indexes indicating the \
+                    - list[torch.Tensor]: Indexes indicating the
                         position of the valid boxes.
-                    - list[torch.Tensor]: Masks indicating which \
+                    - list[torch.Tensor]: Masks indicating which
                         boxes are valid.
         """
         heatmaps, anno_boxes, inds, masks = multi_apply(
@@ -437,14 +437,14 @@ class CenterHead(BaseModule):
             gt_labels_3d (torch.Tensor): Labels of boxes.
 
         Returns:
-            tuple[list[torch.Tensor]]: Tuple of target including \
+            tuple[list[torch.Tensor]]: Tuple of target including
                 the following results in order.
 
                 - list[torch.Tensor]: Heatmap scores.
                 - list[torch.Tensor]: Ground truth boxes.
-                - list[torch.Tensor]: Indexes indicating the position \
+                - list[torch.Tensor]: Indexes indicating the position
                     of the valid boxes.
-                - list[torch.Tensor]: Masks indicating which boxes \
+                - list[torch.Tensor]: Masks indicating which boxes
                     are valid.
         """
         device = gt_labels_3d.device
@@ -728,11 +728,11 @@ class CenterHead(BaseModule):
         Returns:
             list[dict[str: torch.Tensor]]: contains the following keys:
 
-                -bboxes (torch.Tensor): Prediction bboxes after nms with the \
+                -bboxes (torch.Tensor): Prediction bboxes after nms with the
                     shape of [N, 9].
-                -scores (torch.Tensor): Prediction scores after nms with the \
+                -scores (torch.Tensor): Prediction scores after nms with the
                     shape of [N].
-                -labels (torch.Tensor): Prediction labels after nms with the \
+                -labels (torch.Tensor): Prediction labels after nms with the
                     shape of [N].
         """
         predictions_dicts = []
@@ -781,7 +781,7 @@ class CenterHead(BaseModule):
                     boxes_for_nms,
                     top_scores,
                     thresh=self.test_cfg['nms_thr'],
-                    pre_maxsize=self.test_cfg['pre_max_size'],
+                    pre_max_size=self.test_cfg['pre_max_size'],
                     post_max_size=self.test_cfg['post_max_size'])
             else:
                 selected = []

mmdet3d/models/dense_heads/fcos_mono3d_head.py

@@ -21,25 +21,25 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
         num_classes (int): Number of categories excluding the background
             category.
         in_channels (int): Number of channels in the input feature map.
-        regress_ranges (tuple[tuple[int, int]]): Regress range of multiple
+        regress_ranges (tuple[tuple[int, int]], optional): Regress range of multiple
             level points.
-        center_sampling (bool): If true, use center sampling. Default: True.
-        center_sample_radius (float): Radius of center sampling. Default: 1.5.
-        norm_on_bbox (bool): If true, normalize the regression targets
+        center_sampling (bool, optional): If true, use center sampling. Default: True.
+        center_sample_radius (float, optional): Radius of center sampling. Default: 1.5.
+        norm_on_bbox (bool, optional): If true, normalize the regression targets
             with FPN strides. Default: True.
-        centerness_on_reg (bool): If true, position centerness on the
+        centerness_on_reg (bool, optional): If true, position centerness on the
             regress branch. Please refer to https://github.com/tianzhi0549/FCOS/issues/89#issuecomment-516877042.
             Default: True.
-        centerness_alpha: Parameter used to adjust the intensity attenuation
-            from the center to the periphery. Default: 2.5.
-        loss_cls (dict): Config of classification loss.
-        loss_bbox (dict): Config of localization loss.
-        loss_dir (dict): Config of direction classification loss.
-        loss_attr (dict): Config of attribute classification loss.
-        loss_centerness (dict): Config of centerness loss.
-        norm_cfg (dict): dictionary to construct and config norm layer.
+        centerness_alpha (int, optional): Parameter used to adjust the intensity
+            attenuation from the center to the periphery. Default: 2.5.
+        loss_cls (dict, optional): Config of classification loss.
+        loss_bbox (dict, optional): Config of localization loss.
+        loss_dir (dict, optional): Config of direction classification loss.
+        loss_attr (dict, optional): Config of attribute classification loss.
+        loss_centerness (dict, optional): Config of centerness loss.
+        norm_cfg (dict, optional): dictionary to construct and config norm layer.
             Default: norm_cfg=dict(type='GN', num_groups=32, requires_grad=True).
-        centerness_branch (tuple[int]): Channels for centerness branch.
+        centerness_branch (tuple[int], optional): Channels for centerness branch.
             Default: (64, ).
     """  # noqa: E501
 
@@ -153,7 +153,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
                 is True.
 
         Returns:
-            tuple: scores for each class, bbox and direction class \
+            tuple: scores for each class, bbox and direction class
                 predictions, centerness predictions of input feature maps.
         """
         cls_score, bbox_pred, dir_cls_pred, attr_pred, cls_feat, reg_feat = \
@@ -201,7 +201,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
                 the 7th dimension is rotation dimension.
 
         Returns:
-            tuple[torch.Tensor]: ``boxes1`` and ``boxes2`` whose 7th \
+            tuple[torch.Tensor]: ``boxes1`` and ``boxes2`` whose 7th
                 dimensions are changed.
         """
         rad_pred_encoding = torch.sin(boxes1[..., 6:7]) * torch.cos(
@@ -295,7 +295,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
             attr_labels (list[Tensor]): Attributes indices of each box.
             img_metas (list[dict]): Meta information of each image, e.g.,
                 image size, scaling factor, etc.
-            gt_bboxes_ignore (None | list[Tensor]): specify which bounding
+            gt_bboxes_ignore (list[Tensor]): specify which bounding
                 boxes can be ignored when computing the loss.
 
         Returns:
@@ -507,11 +507,11 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
             rescale (bool): If True, return boxes in original image space
 
         Returns:
-            list[tuple[Tensor, Tensor]]: Each item in result_list is 2-tuple. \
-                The first item is an (n, 5) tensor, where the first 4 columns \
-                are bounding box positions (tl_x, tl_y, br_x, br_y) and the \
-                5-th column is a score between 0 and 1. The second item is a \
-                (n,) tensor where each item is the predicted class label of \
+            list[tuple[Tensor, Tensor]]: Each item in result_list is 2-tuple.
+                The first item is an (n, 5) tensor, where the first 4 columns
+                are bounding box positions (tl_x, tl_y, br_x, br_y) and the
+                5-th column is a score between 0 and 1. The second item is a
+                (n,) tensor where each item is the predicted class label of
                 the corresponding box.
         """
         assert len(cls_scores) == len(bbox_preds) == len(dir_cls_preds) == \
@@ -580,7 +580,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
             bbox_preds (list[Tensor]): Box energies / deltas for a single scale
                 level with shape (num_points * bbox_code_size, H, W).
             dir_cls_preds (list[Tensor]): Box scores for direction class
-                predictions on a single scale level with shape \
+                predictions on a single scale level with shape
                 (num_points * 2, H, W)
             attr_preds (list[Tensor]): Attribute scores for each scale level
                 Has shape (N, num_points * num_attrs, H, W)
@@ -700,12 +700,12 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
     def pts2Dto3D(points, view):
         """
         Args:
-            points (torch.Tensor): points in 2D images, [N, 3], \
+            points (torch.Tensor): points in 2D images, [N, 3],
                 3 corresponds with x, y in the image and depth.
             view (np.ndarray): camera instrinsic, [3, 3]
 
         Returns:
-            torch.Tensor: points in 3D space. [N, 3], \
+            torch.Tensor: points in 3D space. [N, 3],
                 3 corresponds with x, y, z in 3D space.
         """
         assert view.shape[0] <= 4
@@ -767,8 +767,8 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
 
         Returns:
             tuple:
-                concat_lvl_labels (list[Tensor]): Labels of each level. \
-                concat_lvl_bbox_targets (list[Tensor]): BBox targets of each \
+                concat_lvl_labels (list[Tensor]): Labels of each level.
+                concat_lvl_bbox_targets (list[Tensor]): BBox targets of each
                     level.
         """
         assert len(points) == len(self.regress_ranges)

mmdet3d/models/dense_heads/groupfree3d_head.py

@@ -25,13 +25,13 @@ class PointsObjClsModule(BaseModule):
 
     Args:
         in_channel (int): number of channels of seed point features.
-        num_convs (int): number of conv layers.
+        num_convs (int, optional): number of conv layers.
             Default: 3.
-        conv_cfg (dict): Config of convolution.
+        conv_cfg (dict, optional): Config of convolution.
             Default: dict(type='Conv1d').
-        norm_cfg (dict): Config of normalization.
+        norm_cfg (dict, optional): Config of normalization.
             Default: dict(type='BN1d').
-        act_cfg (dict): Config of activation.
+        act_cfg (dict, optional): Config of activation.
             Default: dict(type='ReLU').
     """
 
@@ -405,15 +405,15 @@ class GroupFree3DHead(BaseModule):
         Args:
             bbox_preds (dict): Predictions from forward of vote head.
             points (list[torch.Tensor]): Input points.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each sample.
             gt_labels_3d (list[torch.Tensor]): Labels of each sample.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise
+            pts_semantic_mask (list[torch.Tensor]): Point-wise
                 semantic mask.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise
+            pts_instance_mask (list[torch.Tensor]): Point-wise
                 instance mask.
             img_metas (list[dict]): Contain pcd and img's meta info.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
             ret_target (Bool): Return targets or not.
 
@@ -545,12 +545,12 @@ class GroupFree3DHead(BaseModule):
 
         Args:
             points (list[torch.Tensor]): Points of each batch.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): Labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise instance
+            pts_instance_mask (list[torch.Tensor]): Point-wise instance
                 label of each batch.
             bbox_preds (torch.Tensor): Bounding box predictions of vote head.
             max_gt_num (int): Max number of GTs for single batch.
@@ -657,12 +657,12 @@ class GroupFree3DHead(BaseModule):
 
         Args:
             points (torch.Tensor): Points of each batch.
-            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth \
+            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth
                 boxes of each batch.
             gt_labels_3d (torch.Tensor): Labels of each batch.
-            pts_semantic_mask (None | torch.Tensor): Point-wise semantic
+            pts_semantic_mask (torch.Tensor): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | torch.Tensor): Point-wise instance
+            pts_instance_mask (torch.Tensor): Point-wise instance
                 label of each batch.
             max_gt_nums (int): Max number of GTs for single batch.
             seed_points (torch.Tensor): Coordinates of seed points.
@@ -710,7 +710,7 @@ class GroupFree3DHead(BaseModule):
         if self.bbox_coder.with_rot:
             vote_targets = points.new_zeros([num_points, 4 * self.gt_per_seed])
             vote_target_idx = points.new_zeros([num_points], dtype=torch.long)
-            box_indices_all = gt_bboxes_3d.points_in_boxes(points)
+            box_indices_all = gt_bboxes_3d.points_in_boxes_part(points)
             for i in range(gt_labels_3d.shape[0]):
                 box_indices = box_indices_all[:, i]
                 indices = torch.nonzero(
@@ -951,7 +951,7 @@ class GroupFree3DHead(BaseModule):
             box_dim=bbox.shape[-1],
             with_yaw=self.bbox_coder.with_rot,
             origin=(0.5, 0.5, 0.5))
-        box_indices = bbox.points_in_boxes_batch(points)
+        box_indices = bbox.points_in_boxes_all(points)
 
         corner3d = bbox.corners
         minmax_box3d = corner3d.new(torch.Size((corner3d.shape[0], 6)))

mmdet3d/models/dense_heads/parta2_rpn_head.py

@@ -100,20 +100,20 @@ class PartA2RPNHead(Anchor3DHead):
             bbox_preds (list[torch.Tensor]): Multi-level bbox predictions.
             dir_cls_preds (list[torch.Tensor]): Multi-level direction
                 class predictions.
-            gt_bboxes (list[:obj:`BaseInstance3DBoxes`]): Ground truth boxes \
+            gt_bboxes (list[:obj:`BaseInstance3DBoxes`]): Ground truth boxes
                 of each sample.
             gt_labels (list[torch.Tensor]): Labels of each sample.
             input_metas (list[dict]): Point cloud and image's meta info.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:
-            dict[str, list[torch.Tensor]]: Classification, bbox, and \
+            dict[str, list[torch.Tensor]]: Classification, bbox, and
                 direction losses of each level.
 
                 - loss_rpn_cls (list[torch.Tensor]): Classification losses.
                 - loss_rpn_bbox (list[torch.Tensor]): Box regression losses.
-                - loss_rpn_dir (list[torch.Tensor]): Direction classification \
+                - loss_rpn_dir (list[torch.Tensor]): Direction classification
                     losses.
         """
         loss_dict = super().loss(cls_scores, bbox_preds, dir_cls_preds,
@@ -143,7 +143,7 @@ class PartA2RPNHead(Anchor3DHead):
             mlvl_anchors (List[torch.Tensor]): Multi-level anchors
                 in single batch.
             input_meta (list[dict]): Contain pcd and img's meta info.
-            cfg (None | :obj:`ConfigDict`): Training or testing config.
+            cfg (:obj:`ConfigDict`): Training or testing config.
             rescale (list[torch.Tensor]): whether th rescale bbox.
 
         Returns:
@@ -240,7 +240,7 @@ class PartA2RPNHead(Anchor3DHead):
                 Multi-level bbox.
             score_thr (int): Score threshold.
             max_num (int): Max number of bboxes after nms.
-            cfg (None | :obj:`ConfigDict`): Training or testing config.
+            cfg (:obj:`ConfigDict`): Training or testing config.
             input_meta (dict): Contain pcd and img's meta info.
 
         Returns:

mmdet3d/models/dense_heads/shape_aware_head.py

@@ -30,15 +30,17 @@ class BaseShapeHead(BaseModule):
         num_base_anchors (int): Number of anchors per location.
         box_code_size (int): The dimension of boxes to be encoded.
         in_channels (int): Input channels for convolutional layers.
-        shared_conv_channels (tuple): Channels for shared convolutional \
-            layers. Default: (64, 64). \
-        shared_conv_strides (tuple): Strides for shared convolutional \
-            layers. Default: (1, 1).
-        use_direction_classifier (bool, optional): Whether to use direction \
+        shared_conv_channels (tuple, optional): Channels for shared
+            convolutional layers. Default: (64, 64).
+        shared_conv_strides (tuple, optional): Strides for shared
+            convolutional layers. Default: (1, 1).
+        use_direction_classifier (bool, optional): Whether to use direction
             classifier. Default: True.
-        conv_cfg (dict): Config of conv layer. Default: dict(type='Conv2d')
-        norm_cfg (dict): Config of norm layer. Default: dict(type='BN2d').
-        bias (bool|str, optional): Type of bias. Default: False.
+        conv_cfg (dict, optional): Config of conv layer.
+            Default: dict(type='Conv2d')
+        norm_cfg (dict, optional): Config of norm layer.
+            Default: dict(type='BN2d').
+        bias (bool | str, optional): Type of bias. Default: False.
     """
 
     def __init__(self,
@@ -127,11 +129,11 @@ class BaseShapeHead(BaseModule):
                 [B, C, H, W].
 
         Returns:
-            dict[torch.Tensor]: Contain score of each class, bbox \
-                regression and direction classification predictions. \
-                Note that all the returned tensors are reshaped as \
-                [bs*num_base_anchors*H*W, num_cls/box_code_size/dir_bins]. \
-                It is more convenient to concat anchors for different \
+            dict[torch.Tensor]: Contain score of each class, bbox
+                regression and direction classification predictions.
+                Note that all the returned tensors are reshaped as
+                [bs*num_base_anchors*H*W, num_cls/box_code_size/dir_bins].
+                It is more convenient to concat anchors for different
                 classes even though they have different feature map sizes.
         """
         x = self.shared_conv(x)
@@ -168,9 +170,9 @@ class ShapeAwareHead(Anchor3DHead):
 
     Args:
         tasks (dict): Shape-aware groups of multi-class objects.
-        assign_per_class (bool, optional): Whether to do assignment for each \
+        assign_per_class (bool, optional): Whether to do assignment for each
             class. Default: True.
-        kwargs (dict): Other arguments are the same as those in \
+        kwargs (dict): Other arguments are the same as those in
             :class:`Anchor3DHead`.
     """
 
@@ -217,7 +219,7 @@ class ShapeAwareHead(Anchor3DHead):
         Args:
             x (torch.Tensor): Input features.
         Returns:
-            tuple[torch.Tensor]: Contain score of each class, bbox \
+            tuple[torch.Tensor]: Contain score of each class, bbox
                 regression and direction classification predictions.
         """
         results = []
@@ -263,7 +265,7 @@ class ShapeAwareHead(Anchor3DHead):
             num_total_samples (int): The number of valid samples.
 
         Returns:
-            tuple[torch.Tensor]: Losses of class, bbox \
+            tuple[torch.Tensor]: Losses of class, bbox
                 and direction, respectively.
         """
         # classification loss
@@ -325,16 +327,16 @@ class ShapeAwareHead(Anchor3DHead):
                 of each sample.
             gt_labels (list[torch.Tensor]): Gt labels of each sample.
             input_metas (list[dict]): Contain pcd and img's meta info.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:
-            dict[str, list[torch.Tensor]]: Classification, bbox, and \
+            dict[str, list[torch.Tensor]]: Classification, bbox, and
                 direction losses of each level.
 
                 - loss_cls (list[torch.Tensor]): Classification losses.
                 - loss_bbox (list[torch.Tensor]): Box regression losses.
-                - loss_dir (list[torch.Tensor]): Direction classification \
+                - loss_dir (list[torch.Tensor]): Direction classification
                     losses.
         """
         device = cls_scores[0].device
@@ -388,7 +390,7 @@ class ShapeAwareHead(Anchor3DHead):
             dir_cls_preds (list[torch.Tensor]): Multi-level direction
                 class predictions.
             input_metas (list[dict]): Contain pcd and img's meta info.
-            cfg (None | :obj:`ConfigDict`): Training or testing config.
+            cfg (:obj:`ConfigDict`, optional): Training or testing config.
                 Default: None.
             rescale (list[torch.Tensor], optional): Whether to rescale bbox.
                 Default: False.
@@ -443,8 +445,8 @@ class ShapeAwareHead(Anchor3DHead):
             mlvl_anchors (List[torch.Tensor]): Multi-level anchors
                 in single batch.
             input_meta (list[dict]): Contain pcd and img's meta info.
-            cfg (None | :obj:`ConfigDict`): Training or testing config.
-            rescale (list[torch.Tensor], optional): whether to rescale bbox. \
+            cfg (:obj:`ConfigDict`): Training or testing config.
+            rescale (list[torch.Tensor], optional): whether to rescale bbox.
                 Default: False.
 
         Returns:

mmdet3d/models/dense_heads/ssd_3d_head.py

@@ -128,15 +128,15 @@ class SSD3DHead(VoteHead):
         Args:
             bbox_preds (dict): Predictions from forward of SSD3DHead.
             points (list[torch.Tensor]): Input points.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each sample.
             gt_labels_3d (list[torch.Tensor]): Labels of each sample.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise
+            pts_semantic_mask (list[torch.Tensor]): Point-wise
                 semantic mask.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise
+            pts_instance_mask (list[torch.Tensor]): Point-wise
                 instance mask.
             img_metas (list[dict]): Contain pcd and img's meta info.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:
@@ -231,12 +231,12 @@ class SSD3DHead(VoteHead):
 
         Args:
             points (list[torch.Tensor]): Points of each batch.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): Labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise instance
+            pts_instance_mask (list[torch.Tensor]): Point-wise instance
                 label of each batch.
             bbox_preds (torch.Tensor): Bounding box predictions of ssd3d head.
 
@@ -320,12 +320,12 @@ class SSD3DHead(VoteHead):
 
         Args:
             points (torch.Tensor): Points of each batch.
-            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth \
+            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth
                 boxes of each batch.
             gt_labels_3d (torch.Tensor): Labels of each batch.
-            pts_semantic_mask (None | torch.Tensor): Point-wise semantic
+            pts_semantic_mask (torch.Tensor): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | torch.Tensor): Point-wise instance
+            pts_instance_mask (torch.Tensor): Point-wise instance
                 label of each batch.
             aggregated_points (torch.Tensor): Aggregated points from
                 candidate points layer.
@@ -494,7 +494,7 @@ class SSD3DHead(VoteHead):
             origin=(0.5, 0.5, 0.5))
 
         if isinstance(bbox, (LiDARInstance3DBoxes, DepthInstance3DBoxes)):
-            box_indices = bbox.points_in_boxes_batch(points)
+            box_indices = bbox.points_in_boxes_all(points)
             nonempty_box_mask = box_indices.T.sum(1) >= 0
         else:
             raise NotImplementedError('Unsupported bbox type!')
@@ -550,7 +550,7 @@ class SSD3DHead(VoteHead):
                 inside bbox and the index of box where each point are in.
         """
         if isinstance(bboxes_3d, (LiDARInstance3DBoxes, DepthInstance3DBoxes)):
-            points_mask = bboxes_3d.points_in_boxes_batch(points)
+            points_mask = bboxes_3d.points_in_boxes_all(points)
             assignment = points_mask.argmax(dim=-1)
         else:
             raise NotImplementedError('Unsupported bbox type!')

mmdet3d/models/dense_heads/train_mixins.py

@@ -25,7 +25,7 @@ class AnchorTrainMixin(object):
             gt_bboxes_list (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each image.
             input_metas (list[dict]): Meta info of each image.
-            gt_bboxes_ignore_list (None | list): Ignore list of gt bboxes.
+            gt_bboxes_ignore_list (list): Ignore list of gt bboxes.
             gt_labels_list (list[torch.Tensor]): Gt labels of batches.
             label_channels (int): The channel of labels.
             num_classes (int): The number of classes.

mmdet3d/models/dense_heads/vote_head.py

@@ -234,15 +234,15 @@ class VoteHead(BaseModule):
         Args:
             bbox_preds (dict): Predictions from forward of vote head.
             points (list[torch.Tensor]): Input points.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each sample.
             gt_labels_3d (list[torch.Tensor]): Labels of each sample.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise
+            pts_semantic_mask (list[torch.Tensor]): Point-wise
                 semantic mask.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise
+            pts_instance_mask (list[torch.Tensor]): Point-wise
                 instance mask.
             img_metas (list[dict]): Contain pcd and img's meta info.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
             ret_target (Bool): Return targets or not.
 
@@ -358,12 +358,12 @@ class VoteHead(BaseModule):
 
         Args:
             points (list[torch.Tensor]): Points of each batch.
-            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth \
+            gt_bboxes_3d (list[:obj:`BaseInstance3DBoxes`]): Ground truth
                 bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): Labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): Point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): Point-wise instance
+            pts_instance_mask (list[torch.Tensor]): Point-wise instance
                 label of each batch.
             bbox_preds (torch.Tensor): Bounding box predictions of vote head.
 
@@ -447,12 +447,12 @@ class VoteHead(BaseModule):
 
         Args:
             points (torch.Tensor): Points of each batch.
-            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth \
+            gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): Ground truth
                 boxes of each batch.
             gt_labels_3d (torch.Tensor): Labels of each batch.
-            pts_semantic_mask (None | torch.Tensor): Point-wise semantic
+            pts_semantic_mask (torch.Tensor): Point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | torch.Tensor): Point-wise instance
+            pts_instance_mask (torch.Tensor): Point-wise instance
                 label of each batch.
             aggregated_points (torch.Tensor): Aggregated points from
                 vote aggregation layer.
@@ -471,7 +471,7 @@ class VoteHead(BaseModule):
             vote_target_masks = points.new_zeros([num_points],
                                                  dtype=torch.long)
             vote_target_idx = points.new_zeros([num_points], dtype=torch.long)
-            box_indices_all = gt_bboxes_3d.points_in_boxes_batch(points)
+            box_indices_all = gt_bboxes_3d.points_in_boxes_all(points)
             for i in range(gt_labels_3d.shape[0]):
                 box_indices = box_indices_all[:, i]
                 indices = torch.nonzero(
@@ -621,7 +621,7 @@ class VoteHead(BaseModule):
             box_dim=bbox.shape[-1],
             with_yaw=self.bbox_coder.with_rot,
             origin=(0.5, 0.5, 0.5))
-        box_indices = bbox.points_in_boxes_batch(points)
+        box_indices = bbox.points_in_boxes_all(points)
 
         corner3d = bbox.corners
         minmax_box3d = corner3d.new(torch.Size((corner3d.shape[0], 6)))

mmdet3d/models/detectors/centerpoint.py

@@ -97,7 +97,8 @@ class CenterPoint(MVXTwoStageDetector):
         Args:
             feats (list[torch.Tensor]): Feature of point cloud.
             img_metas (list[dict]): Meta information of samples.
-            rescale (bool): Whether to rescale bboxes. Default: False.
+            rescale (bool, optional): Whether to rescale bboxes.
+                Default: False.
 
         Returns:
             dict: Returned bboxes consists of the following keys:

mmdet3d/models/detectors/groupfree3dnet.py

@@ -38,11 +38,11 @@ class GroupFree3DNet(SingleStage3DDetector):
             img_metas (list): Image metas.
             gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): gt bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): gt class labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): point-wise instance
+            pts_instance_mask (list[torch.Tensor]): point-wise instance
                 label of each batch.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:

mmdet3d/models/detectors/h3dnet.py

@@ -47,11 +47,11 @@ class H3DNet(TwoStage3DDetector):
             img_metas (list): Image metas.
             gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): gt bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): gt class labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): point-wise instance
+            pts_instance_mask (list[torch.Tensor]): point-wise instance
                 label of each batch.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:

mmdet3d/models/detectors/imvotenet.py

@@ -149,21 +149,21 @@ class ImVoteNet(Base3DDetector):
 
         if self.with_img_backbone:
             if img_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.img_backbone.init_cfg = dict(
                     type='Pretrained', checkpoint=img_pretrained)
         if self.with_img_roi_head:
             if img_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.img_roi_head.init_cfg = dict(
                     type='Pretrained', checkpoint=img_pretrained)
 
         if self.with_pts_backbone:
             if img_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.pts_backbone.init_cfg = dict(
                     type='Pretrained', checkpoint=pts_pretrained)
 
@@ -393,9 +393,9 @@ class ImVoteNet(Base3DDetector):
                 with shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
             gt_labels (list[torch.Tensor]): class indices for each
                 2d bounding box.
-            gt_bboxes_ignore (None | list[torch.Tensor]): specify which
+            gt_bboxes_ignore (list[torch.Tensor]): specify which
                 2d bounding boxes can be ignored when computing the loss.
-            gt_masks (None | torch.Tensor): true segmentation masks for each
+            gt_masks (torch.Tensor): true segmentation masks for each
                 2d bbox, used if the architecture supports a segmentation task.
             proposals: override rpn proposals (2d) with custom proposals.
                 Use when `with_rpn` is False.
@@ -403,9 +403,9 @@ class ImVoteNet(Base3DDetector):
                 not supported yet.
             gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): 3d gt bboxes.
             gt_labels_3d (list[torch.Tensor]): gt class labels for 3d bboxes.
-            pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): point-wise instance
+            pts_instance_mask (list[torch.Tensor]): point-wise instance
                 label of each batch.
 
         Returns:

mmdet3d/models/detectors/mvx_two_stage.py

@@ -84,21 +84,21 @@ class MVXTwoStageDetector(Base3DDetector):
 
         if self.with_img_backbone:
             if img_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.img_backbone.init_cfg = dict(
                     type='Pretrained', checkpoint=img_pretrained)
         if self.with_img_roi_head:
             if img_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.img_roi_head.init_cfg = dict(
                     type='Pretrained', checkpoint=img_pretrained)
 
         if self.with_pts_backbone:
-            if pts_pretrained is not None:
-                warnings.warn('DeprecationWarning: pretrained is a deprecated \
-                    key, please consider using init_cfg')
+            if img_pretrained is not None:
+                warnings.warn('DeprecationWarning: pretrained is a deprecated '
+                              'key, please consider using init_cfg.')
                 self.pts_backbone.init_cfg = dict(
                     type='Pretrained', checkpoint=pts_pretrained)
 
@@ -260,7 +260,7 @@ class MVXTwoStageDetector(Base3DDetector):
                 of 2D boxes in images. Defaults to None.
             gt_bboxes (list[torch.Tensor], optional): Ground truth 2D boxes in
                 images. Defaults to None.
-            img (torch.Tensor optional): Images of each sample with shape
+            img (torch.Tensor, optional): Images of each sample with shape
                 (N, C, H, W). Defaults to None.
             proposals ([list[torch.Tensor], optional): Predicted proposals
                 used for training Fast RCNN. Defaults to None.

mmdet3d/models/detectors/single_stage_mono3d.py

@@ -48,14 +48,15 @@ class SingleStageMono3DDetector(SingleStageDetector):
                 image in [tl_x, tl_y, br_x, br_y] format.
             gt_labels (list[Tensor]): Class indices corresponding to each box
             gt_bboxes_3d (list[Tensor]): Each item are the 3D truth boxes for
-                each image in [x, y, z, w, l, h, theta, vx, vy] format.
+                each image in [x, y, z, x_size, y_size, z_size, yaw, vx, vy]
+                format.
             gt_labels_3d (list[Tensor]): 3D class indices corresponding to
                 each box.
             centers2d (list[Tensor]): Projected 3D centers onto 2D images.
             depths (list[Tensor]): Depth of projected centers on 2D images.
             attr_labels (list[Tensor], optional): Attribute indices
                 corresponding to each box
-            gt_bboxes_ignore (None | list[Tensor]): Specify which bounding
+            gt_bboxes_ignore (list[Tensor]): Specify which bounding
                 boxes can be ignored when computing the loss.
 
         Returns:

mmdet3d/models/detectors/votenet.py

@@ -40,11 +40,11 @@ class VoteNet(SingleStage3DDetector):
             img_metas (list): Image metas.
             gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): gt bboxes of each batch.
             gt_labels_3d (list[torch.Tensor]): gt class labels of each batch.
-            pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
+            pts_semantic_mask (list[torch.Tensor]): point-wise semantic
                 label of each batch.
-            pts_instance_mask (None | list[torch.Tensor]): point-wise instance
+            pts_instance_mask (list[torch.Tensor]): point-wise instance
                 label of each batch.
-            gt_bboxes_ignore (None | list[torch.Tensor]): Specify
+            gt_bboxes_ignore (list[torch.Tensor]): Specify
                 which bounding.
 
         Returns:

mmdet3d/models/fusion_layers/point_fusion.py

@@ -34,7 +34,7 @@ def point_sample(img_meta,
         coord_type (str): 'DEPTH' or 'CAMERA' or 'LIDAR'.
         img_scale_factor (torch.Tensor): Scale factor with shape of \
             (w_scale, h_scale).
-        img_crop_offset (torch.Tensor): Crop offset used to crop \
+        img_crop_offset (torch.Tensor): Crop offset used to crop
             image during data augmentation with shape of (w_offset, h_offset).
         img_flip (bool): Whether the image is flipped.
         img_pad_shape (tuple[int]): int tuple indicates the h & w after

mmdet3d/models/losses/axis_aligned_iou_loss.py

@@ -54,7 +54,7 @@ class AxisAlignedIoULoss(nn.Module):
         Args:
             pred (torch.Tensor): Bbox predictions with shape [..., 3].
             target (torch.Tensor): Bbox targets (gt) with shape [..., 3].
-            weight (torch.Tensor|float, optional): Weight of loss. \
+            weight (torch.Tensor | float, optional): Weight of loss.
                 Defaults to None.
             avg_factor (int, optional): Average factor that is used to average
                 the loss. Defaults to None.

mmdet3d/models/losses/chamfer_distance.py

@@ -29,13 +29,13 @@ def chamfer_distance(src,
     Returns:
         tuple: Source and Destination loss with the corresponding indices.
 
-            - loss_src (torch.Tensor): The min distance \
+            - loss_src (torch.Tensor): The min distance
                 from source to destination.
-            - loss_dst (torch.Tensor): The min distance \
+            - loss_dst (torch.Tensor): The min distance
                 from destination to source.
-            - indices1 (torch.Tensor): Index the min distance point \
+            - indices1 (torch.Tensor): Index the min distance point
                 for each point in source to destination.
-            - indices2 (torch.Tensor): Index the min distance point \
+            - indices2 (torch.Tensor): Index the min distance point
                 for each point in destination to source.
     """
 
@@ -125,10 +125,10 @@ class ChamferDistance(nn.Module):
                 Defaults to False.
 
         Returns:
-            tuple[torch.Tensor]: If ``return_indices=True``, return losses of \
-                source and target with their corresponding indices in the \
-                order of ``(loss_source, loss_target, indices1, indices2)``. \
-                If ``return_indices=False``, return \
+            tuple[torch.Tensor]: If ``return_indices=True``, return losses of
+                source and target with their corresponding indices in the
+                order of ``(loss_source, loss_target, indices1, indices2)``.
+                If ``return_indices=False``, return
                 ``(loss_source, loss_target)``.
         """
         assert reduction_override in (None, 'none', 'mean', 'sum')

mmdet3d/models/middle_encoders/sparse_encoder.py

@@ -14,19 +14,21 @@ class SparseEncoder(nn.Module):
     Args:
         in_channels (int): The number of input channels.
         sparse_shape (list[int]): The sparse shape of input tensor.
-        order (list[str]): Order of conv module. Defaults to ('conv',
-            'norm', 'act').
-        norm_cfg (dict): Config of normalization layer. Defaults to
+        order (list[str], optional): Order of conv module.
+            Defaults to ('conv', 'norm', 'act').
+        norm_cfg (dict, optional): Config of normalization layer. Defaults to
             dict(type='BN1d', eps=1e-3, momentum=0.01).
-        base_channels (int): Out channels for conv_input layer.
+        base_channels (int, optional): Out channels for conv_input layer.
             Defaults to 16.
-        output_channels (int): Out channels for conv_out layer.
+        output_channels (int, optional): Out channels for conv_out layer.
             Defaults to 128.
-        encoder_channels (tuple[tuple[int]]):
+        encoder_channels (tuple[tuple[int]], optional):
             Convolutional channels of each encode block.
-        encoder_paddings (tuple[tuple[int]]): Paddings of each encode block.
+        encoder_paddings (tuple[tuple[int]], optional):
+            Paddings of each encode block.
             Defaults to ((16, ), (32, 32, 32), (64, 64, 64), (64, 64, 64)).
-        block_type (str): Type of the block to use. Defaults to 'conv_module'.
+        block_type (str, optional): Type of the block to use.
+            Defaults to 'conv_module'.
     """
 
     def __init__(self,
@@ -99,7 +101,7 @@ class SparseEncoder(nn.Module):
 
         Args:
             voxel_features (torch.float32): Voxel features in shape (N, C).
-            coors (torch.int32): Coordinates in shape (N, 4), \
+            coors (torch.int32): Coordinates in shape (N, 4),
                 the columns in the order of (batch_idx, z_idx, y_idx, x_idx).
             batch_size (int): Batch size.
 
@@ -139,9 +141,9 @@ class SparseEncoder(nn.Module):
             make_block (method): A bounded function to build blocks.
             norm_cfg (dict[str]): Config of normalization layer.
             in_channels (int): The number of encoder input channels.
-            block_type (str): Type of the block to use. Defaults to
-                'conv_module'.
-            conv_cfg (dict): Config of conv layer. Defaults to
+            block_type (str, optional): Type of the block to use.
+                Defaults to 'conv_module'.
+            conv_cfg (dict, optional): Config of conv layer. Defaults to
                 dict(type='SubMConv3d').
 
         Returns:

mmdet3d/models/model_utils/transformer.py

@@ -15,15 +15,16 @@ class GroupFree3DMHA(MultiheadAttention):
         embed_dims (int): The embedding dimension.
         num_heads (int): Parallel attention heads. Same as
             `nn.MultiheadAttention`.
-        attn_drop (float): A Dropout layer on attn_output_weights. Default 0.0.
-        proj_drop (float): A Dropout layer. Default 0.0.
-        dropout_layer (obj:`ConfigDict`): The dropout_layer used
+        attn_drop (float, optional): A Dropout layer on attn_output_weights.
+            Defaults to 0.0.
+        proj_drop (float, optional): A Dropout layer. Defaults to 0.0.
+        dropout_layer (obj:`ConfigDict`, optional): The dropout_layer used
             when adding the shortcut.
-        init_cfg (obj:`mmcv.ConfigDict`): The Config for initialization.
-            Default: None.
-        batch_first (bool): Key, Query and Value are shape of
+        init_cfg (obj:`mmcv.ConfigDict`, optional): The Config for
+            initialization. Default: None.
+        batch_first (bool, optional): Key, Query and Value are shape of
             (batch, n, embed_dim)
-            or (n, batch, embed_dim). Default to False.
+            or (n, batch, embed_dim). Defaults to False.
     """
 
     def __init__(self,
@@ -58,26 +59,26 @@ class GroupFree3DMHA(MultiheadAttention):
                 embed_dims]. Same in `nn.MultiheadAttention.forward`.
             key (Tensor): The key tensor with shape [num_keys, bs,
                 embed_dims]. Same in `nn.MultiheadAttention.forward`.
-                If None, the ``query`` will be used. Defaults to None.
+                If None, the ``query`` will be used.
             value (Tensor): The value tensor with same shape as `key`.
-                Same in `nn.MultiheadAttention.forward`. Defaults to None.
+                Same in `nn.MultiheadAttention.forward`.
                 If None, the `key` will be used.
             identity (Tensor): This tensor, with the same shape as x,
-                will be used for the identity link.
-                If None, `x` will be used. Defaults to None.
-            query_pos (Tensor): The positional encoding for query, with
-                the same shape as `x`. If not None, it will
-                be added to `x` before forward function. Defaults to None.
-            key_pos (Tensor): The positional encoding for `key`, with the
-                same shape as `key`. Defaults to None. If not None, it will
-                be added to `key` before forward function. If None, and
-                `query_pos` has the same shape as `key`, then `query_pos`
+                will be used for the identity link. If None, `x` will be used.
+            query_pos (Tensor, optional): The positional encoding for query,
+                with the same shape as `x`. Defaults to None.
+                If not None, it will be added to `x` before forward function.
+            key_pos (Tensor, optional): The positional encoding for `key`,
+                with the same shape as `key`. Defaults to None. If not None,
+                it will be added to `key` before forward function. If None,
+                and `query_pos` has the same shape as `key`, then `query_pos`
                 will be used for `key_pos`. Defaults to None.
-            attn_mask (Tensor): ByteTensor mask with shape [num_queries,
-                num_keys]. Same in `nn.MultiheadAttention.forward`.
-                Defaults to None.
-            key_padding_mask (Tensor): ByteTensor with shape [bs, num_keys].
+            attn_mask (Tensor, optional): ByteTensor mask with shape
+                [num_queries, num_keys].
                 Same in `nn.MultiheadAttention.forward`. Defaults to None.
+            key_padding_mask (Tensor, optional): ByteTensor with shape
+                [bs, num_keys]. Same in `nn.MultiheadAttention.forward`.
+                Defaults to None.
 
         Returns:
             Tensor: forwarded results with shape [num_queries, bs, embed_dims].
@@ -113,7 +114,7 @@ class ConvBNPositionalEncoding(nn.Module):
 
     Args:
         input_channel (int): input features dim.
-        num_pos_feats (int): output position features dim.
+        num_pos_feats (int, optional): output position features dim.
             Defaults to 288 to be consistent with seed features dim.
     """