Add code-spell pre-commit hook and fix typos (#995)

mmdet3d/datasets/pipelines/transforms_3d.py

@@ -151,7 +151,7 @@ class RandomFlip3D(RandomFlip):
                 'pcd_horizontal_flip' and 'pcd_vertical_flip' keys are added
                 into result dict.
         """
-        # filp 2D image and its annotations
+        # flip 2D image and its annotations
         super(RandomFlip3D, self).__call__(input_dict)
 
         if self.sync_2d:
@@ -921,11 +921,11 @@ class PointSample(object):
         """
         points = results['points']
         # Points in Camera coord can provide the depth information.
-        # TODO: Need to suport distance-based sampling for other coord system.
+        # TODO: Need to support distance-based sampling for other coord system.
         if self.sample_range is not None:
             from mmdet3d.core.points import CameraPoints
-            assert isinstance(points, CameraPoints), \
-                'Sampling based on distance is only appliable for CAMERA coord'
+            assert isinstance(points, CameraPoints), 'Sampling based on' \
+                'distance is only applicable for CAMERA coord'
         points, choices = self._points_random_sampling(
             points,
             self.num_points,
@@ -1293,7 +1293,7 @@ class VoxelBasedPointSampler(object):
     Args:
         cur_sweep_cfg (dict): Config for sampling current points.
         prev_sweep_cfg (dict): Config for sampling previous points.
-        time_dim (int): Index that indicate the time dimention
+        time_dim (int): Index that indicate the time dimension
             for input points.
     """
 
@@ -1317,7 +1317,7 @@ class VoxelBasedPointSampler(object):
             points (np.ndarray): Points subset to be sampled.
             sampler (VoxelGenerator): Voxel based sampler for
                 each points subset.
-            point_dim (int): The dimention of each points
+            point_dim (int): The dimension of each points
 
         Returns:
             np.ndarray: Sampled points.
@@ -1398,7 +1398,7 @@ class VoxelBasedPointSampler(object):
             points_numpy = points_numpy.squeeze(1)
         results['points'] = points.new_point(points_numpy[..., :original_dim])
 
-        # Restore the correspoinding seg and mask fields
+        # Restore the corresponding seg and mask fields
         for key, dim_index in map_fields2dim:
             results[key] = points_numpy[..., dim_index]
 
@@ -1551,7 +1551,7 @@ class AffineResize(object):
             results[key] = bboxes
 
     def _affine_transform(self, points, matrix):
-        """Affine transform bbox points to input iamge.
+        """Affine transform bbox points to input image.
 
         Args:
             points (np.ndarray): Points to be transformed.
@@ -1605,10 +1605,10 @@ class AffineResize(object):
         return matrix.astype(np.float32)
 
     def _get_ref_point(self, ref_point1, ref_point2):
-        """Get reference point to calculate affine transfrom matrix.
+        """Get reference point to calculate affine transform matrix.
 
         While using opencv to calculate the affine matrix, we need at least
-        three corresponding points seperately on original image and target
+        three corresponding points separately on original image and target
         image. Here we use two points to get the the third reference point.
         """
         d = ref_point1 - ref_point2
@@ -1628,7 +1628,7 @@ class RandomShiftScale(object):
 
     Different from the normal shift and scale function, it doesn't
     directly shift or scale image. It can record the shift and scale
-    infos into loading pipelines. It's desgined to be used with
+    infos into loading pipelines. It's designed to be used with
     AffineResize together.
 
     Args:

mmdet3d/datasets/waymo_dataset.py

@@ -234,7 +234,7 @@ class WaymoDataset(KittiDataset):
             pklfile_prefix (str, optional): The prefix of pkl files including
                 the file path and the prefix of filename, e.g., "a/b/prefix".
                 If not specified, a temp file will be created. Default: None.
-            submission_prefix (str, optional): The prefix of submission datas.
+            submission_prefix (str, optional): The prefix of submission data.
                 If not specified, the submission data will not be generated.
             show (bool, optional): Whether to visualize.
                 Default: False.

mmdet3d/models/backbones/nostem_regnet.py

@@ -16,7 +16,7 @@ class NoStemRegNet(RegNet):
             - wm (float): Quantization parameter to quantize the width.
             - depth (int): Depth of the backbone.
             - group_w (int): Width of group.
-            - bot_mul (float): Bottleneck ratio, i.e. expansion of bottlneck.
+            - bot_mul (float): Bottleneck ratio, i.e. expansion of bottleneck.
         strides (Sequence[int]): Strides of the first block of each stage.
         base_channels (int): Base channels after stem layer.
         in_channels (int): Number of input image channels. Normally 3.

mmdet3d/models/dense_heads/anchor_free_mono3d_head.py

@@ -321,7 +321,7 @@ class AnchorFreeMono3DHead(BaseMono3DDenseHead):
         return multi_apply(self.forward_single, feats)[:5]
 
     def forward_single(self, x):
-        """Forward features of a single scale levle.
+        """Forward features of a single scale level.
 
         Args:
             x (Tensor): FPN feature maps of the specified stride.

mmdet3d/models/dense_heads/centerpoint_head.py

@@ -23,8 +23,8 @@ class SeparateHead(BaseModule):
         heads (dict): Conv information.
         head_conv (int, optional): Output channels.
             Default: 64.
-        final_kernal (int, optional): Kernal size for the last conv layer.
-            Deafult: 1.
+        final_kernal (int, optional): Kernel size for the last conv layer.
+            Default: 1.
         init_bias (float, optional): Initial bias. Default: -2.19.
         conv_cfg (dict, optional): Config of conv layer.
             Default: dict(type='Conv2d')
@@ -136,8 +136,8 @@ class DCNSeparateHead(BaseModule):
         dcn_config (dict): Config of dcn layer.
         head_conv (int, optional): Output channels.
             Default: 64.
-        final_kernal (int, optional): Kernal size for the last conv
-            layer. Deafult: 1.
+        final_kernal (int, optional): Kernel size for the last conv
+            layer. Default: 1.
         init_bias (float, optional): Initial bias. Default: -2.19.
         conv_cfg (dict, optional): Config of conv layer.
             Default: dict(type='Conv2d')

mmdet3d/models/dense_heads/fcos_mono3d_head.py

@@ -151,7 +151,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
                            self.strides)[:5]
 
     def forward_single(self, x, scale, stride):
-        """Forward features of a single scale levle.
+        """Forward features of a single scale level.
 
         Args:
             x (Tensor): FPN feature maps of the specified stride.
@@ -691,7 +691,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
         Args:
             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]
+            view (np.ndarray): camera intrinsic, [3, 3]
 
         Returns:
             torch.Tensor: points in 3D space. [N, 3],
@@ -713,7 +713,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
         viewpad[:view.shape[0], :view.shape[1]] = points2D.new_tensor(view)
         inv_viewpad = torch.inverse(viewpad).transpose(0, 1)
 
-        # Do operation in homogenous coordinates.
+        # Do operation in homogeneous coordinates.
         nbr_points = unnorm_points2D.shape[0]
         homo_points2D = torch.cat(
             [unnorm_points2D,

mmdet3d/models/dense_heads/groupfree3d_head.py

@@ -299,7 +299,7 @@ class GroupFree3DHead(BaseModule):
         """Forward pass.
 
         Note:
-            The forward of GroupFree3DHead is devided into 2 steps:
+            The forward of GroupFree3DHead is divided into 2 steps:
 
                 1. Initial object candidates sampling.
                 2. Iterative object box prediction by transformer decoder.
@@ -880,7 +880,7 @@ class GroupFree3DHead(BaseModule):
         Returns:
             list[tuple[torch.Tensor]]: Bounding boxes, scores and labels.
         """
-        # support multi-stage predicitons
+        # support multi-stage predictions
         assert self.test_cfg['prediction_stages'] in \
             ['last', 'all', 'last_three']
 

mmdet3d/models/dense_heads/parta2_rpn_head.py

@@ -207,7 +207,7 @@ class PartA2RPNHead(Anchor3DHead):
         mlvl_dir_scores = torch.cat(mlvl_dir_scores)
         # shape [k, num_class] before sigmoid
         # PartA2 need to keep raw classification score
-        # becase the bbox head in the second stage does not have
+        # because the bbox head in the second stage does not have
         # classification branch,
         # roi head need this score as classification score
         mlvl_cls_score = torch.cat(mlvl_cls_score)

mmdet3d/models/dense_heads/smoke_mono3d_head.py

@@ -25,9 +25,9 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
         num_classes (int): Number of categories excluding the background
             category.
         in_channels (int): Number of channels in the input feature map.
-        dim_channel (list[int]): indexs of dimension offset preds in
+        dim_channel (list[int]): indices of dimension offset preds in
             regression heatmap channels.
-        ori_channel (list[int]): indexs of orientation offset pred in
+        ori_channel (list[int]): indices of orientation offset pred in
             regression heatmap channels.
         bbox_coder (:obj:`CameraInstance3DBoxes`): Bbox coder
             for encoding and decoding boxes.
@@ -221,12 +221,12 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
         return batch_bboxes, batch_scores, batch_topk_labels
 
     def get_predictions(self, labels3d, centers2d, gt_locations, gt_dimensions,
-                        gt_orientations, indexs, img_metas, pred_reg):
+                        gt_orientations, indices, img_metas, pred_reg):
         """Prepare predictions for computing loss.
 
         Args:
             labels3d (Tensor): Labels of each 3D box.
-                shpae (B, max_objs, )
+                shape (B, max_objs, )
             centers2d (Tensor): Coords of each projected 3D box
                 center on image. shape (B * max_objs, 2)
             gt_locations (Tensor): Coords of each 3D box's location.
@@ -235,7 +235,7 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
                 shape (N, 3)
             gt_orientations (Tensor): Orientation(yaw) of each 3D box.
                 shape (N, 1)
-            indexs (Tensor): Indexs of the existence of the 3D box.
+            indices (Tensor): Indices of the existence of the 3D box.
                 shape (B * max_objs, )
             img_metas (list[dict]): Meta information of each image,
                 e.g., image size, scaling factor, etc.
@@ -247,7 +247,7 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
             - bbox3d_yaws (:obj:`CameraInstance3DBoxes`):
                 bbox calculated using pred orientations.
             - bbox3d_dims (:obj:`CameraInstance3DBoxes`):
-                bbox calculated using pred dimentions.
+                bbox calculated using pred dimensions.
             - bbox3d_locs (:obj:`CameraInstance3DBoxes`):
                 bbox calculated using pred locations.
         """
@@ -269,12 +269,12 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
             pred_regression_pois, centers2d, labels3d, cam2imgs, trans_mats,
             gt_locations)
 
-        locations, dimensions, orientations = locations[indexs], dimensions[
-            indexs], orientations[indexs]
+        locations, dimensions, orientations = locations[indices], dimensions[
+            indices], orientations[indices]
 
         locations[:, 1] += dimensions[:, 1] / 2
 
-        gt_locations = gt_locations[indexs]
+        gt_locations = gt_locations[indices]
 
         assert len(locations) == len(gt_locations)
         assert len(dimensions) == len(gt_dimensions)
@@ -293,7 +293,7 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
     def get_targets(self, gt_bboxes, gt_labels, gt_bboxes_3d, gt_labels_3d,
                     centers2d, feat_shape, img_shape, img_metas):
         """Get training targets for batch images.
-``
+
         Args:
             gt_bboxes (list[Tensor]): Ground truth bboxes of each image,
                 shape (num_gt, 4).
@@ -318,10 +318,10 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
               - gt_centers2d (Tensor): Coords of each projected 3D box
                     center on image. shape (B * max_objs, 2)
               - gt_labels3d (Tensor): Labels of each 3D box.
-                    shpae (B, max_objs, )
-              - indexs (Tensor): Indexs of the existence of the 3D box.
+                    shape (B, max_objs, )
+              - indices (Tensor): Indices of the existence of the 3D box.
                     shape (B * max_objs, )
-              - affine_indexs (Tensor): Indexs of the affine of the 3D box.
+              - affine_indices (Tensor): Indices of the affine of the 3D box.
                     shape (N, )
               - gt_locs (Tensor): Coords of each 3D box's location.
                     shape (N, 3)
@@ -417,8 +417,8 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
         target_labels = dict(
             gt_centers2d=batch_centers2d.long(),
             gt_labels3d=batch_labels_3d,
-            indexs=inds,
-            reg_indexs=reg_inds,
+            indices=inds,
+            reg_indices=reg_inds,
             gt_locs=batch_gt_locations,
             gt_dims=gt_dimensions,
             gt_yaws=gt_orientations,
@@ -487,14 +487,14 @@ class SMOKEMono3DHead(AnchorFreeMono3DHead):
             gt_locations=target_labels['gt_locs'],
             gt_dimensions=target_labels['gt_dims'],
             gt_orientations=target_labels['gt_yaws'],
-            indexs=target_labels['indexs'],
+            indices=target_labels['indices'],
             img_metas=img_metas,
             pred_reg=pred_reg)
 
         loss_cls = self.loss_cls(
             center2d_heatmap, center2d_heatmap_target, avg_factor=avg_factor)
 
-        reg_inds = target_labels['reg_indexs']
+        reg_inds = target_labels['reg_indices']
 
         loss_bbox_oris = self.loss_bbox(
             pred_bboxes['ori'].corners[reg_inds, ...],

mmdet3d/models/dense_heads/train_mixins.py

@@ -35,7 +35,7 @@ class AnchorTrainMixin(object):
             tuple (list, list, list, list, list, list, int, int):
                 Anchor targets, including labels, label weights,
                 bbox targets, bbox weights, direction targets,
-                direction weights, number of postive anchors and
+                direction weights, number of positive anchors and
                 number of negative anchors.
         """
         num_imgs = len(input_metas)

mmdet3d/models/dense_heads/vote_head.py

@@ -136,7 +136,7 @@ class VoteHead(BaseModule):
         """Forward pass.
 
         Note:
-            The forward of VoteHead is devided into 4 steps:
+            The forward of VoteHead is divided into 4 steps:
 
                 1. Generate vote_points from seed_points.
                 2. Aggregate vote_points.

mmdet3d/models/detectors/base.py

@@ -103,6 +103,6 @@ class Base3DDetector(BaseDetector):
                                                 Box3DMode.DEPTH)
             elif box_mode_3d != Box3DMode.DEPTH:
                 ValueError(
-                    f'Unsupported box_mode_3d {box_mode_3d} for convertion!')
+                    f'Unsupported box_mode_3d {box_mode_3d} for conversion!')
             pred_bboxes = pred_bboxes.tensor.cpu().numpy()
             show_result(points, None, pred_bboxes, out_dir, file_name)

mmdet3d/models/detectors/mvx_two_stage.py

@@ -497,7 +497,7 @@ class MVXTwoStageDetector(Base3DDetector):
                                                 Box3DMode.DEPTH)
             elif box_mode_3d != Box3DMode.DEPTH:
                 ValueError(
-                    f'Unsupported box_mode_3d {box_mode_3d} for convertion!')
+                    f'Unsupported box_mode_3d {box_mode_3d} for conversion!')
 
             pred_bboxes = pred_bboxes.tensor.cpu().numpy()
             show_result(points, None, pred_bboxes, out_dir, file_name)

mmdet3d/models/model_utils/transformer.py

@@ -132,7 +132,7 @@ class ConvBNPositionalEncoding(nn.Module):
             xyz (Tensor)： (B, N, 3) the coordinates to embed.
 
         Returns:
-            Tensor: (B, num_pos_feats, N) the embeded position features.
+            Tensor: (B, num_pos_feats, N) the embedded position features.
         """
         xyz = xyz.permute(0, 2, 1)
         position_embedding = self.position_embedding_head(xyz)

mmdet3d/models/necks/dla_neck.py

@@ -172,7 +172,7 @@ class DLANeck(BaseModule):
     Args:
         in_channels (list[int], optional): List of input channels
             of multi-scale feature map.
-        start_level (int, optioanl): The scale level where upsampling
+        start_level (int, optional): The scale level where upsampling
             starts. Default: 2.
         end_level (int, optional): The scale level where upsampling
             ends. Default: 5.

mmdet3d/models/roi_heads/bbox_heads/h3d_bbox_head.py

@@ -20,7 +20,7 @@ class H3DBboxHead(BaseModule):
 
     Args:
         num_classes (int): The number of classes.
-        suface_matching_cfg (dict): Config for suface primitive matching.
+        surface_matching_cfg (dict): Config for surface primitive matching.
         line_matching_cfg (dict): Config for line primitive matching.
         bbox_coder (:obj:`BaseBBoxCoder`): Bbox coder for encoding and
             decoding boxes.
@@ -36,7 +36,7 @@ class H3DBboxHead(BaseModule):
         primitive_refine_channels (tuple[int]): Convolution channels of
             prediction layer.
         upper_thresh (float): Threshold for line matching.
-        surface_thresh (float): Threshold for suface matching.
+        surface_thresh (float): Threshold for surface matching.
         line_thresh (float): Threshold for line matching.
         conv_cfg (dict): Config of convolution in prediction layer.
         norm_cfg (dict): Config of BN in prediction layer.

mmdet3d/models/roi_heads/bbox_heads/parta2_bbox_head.py

@@ -574,7 +574,7 @@ class PartA2BboxHead(BaseModule):
             box_preds (torch.Tensor): Predicted boxes in shape (N, 7+C).
             score_thr (float): Threshold of scores.
             nms_thr (float): Threshold for NMS.
-            input_meta (dict): Meta informations of the current sample.
+            input_meta (dict): Meta information of the current sample.
             use_rotate_nms (bool, optional): Whether to use rotated nms.
                 Defaults to True.
 

mmdet3d/models/roi_heads/mask_heads/primitive_head.py

@@ -20,7 +20,7 @@ class PrimitiveHead(BaseModule):
         num_dims (int): The dimension of primitive semantic information.
         num_classes (int): The number of class.
         primitive_mode (str): The mode of primitive module,
-            avaliable mode ['z', 'xy', 'line'].
+            available mode ['z', 'xy', 'line'].
         bbox_coder (:obj:`BaseBBoxCoder`): Bbox coder for encoding and
             decoding boxes.
         train_cfg (dict): Config for training.
@@ -30,7 +30,7 @@ class PrimitiveHead(BaseModule):
         feat_channels (tuple[int]): Convolution channels of
             prediction layer.
         upper_thresh (float): Threshold for line matching.
-        surface_thresh (float): Threshold for suface matching.
+        surface_thresh (float): Threshold for surface matching.
         conv_cfg (dict): Config of convolution in prediction layer.
         norm_cfg (dict): Config of BN in prediction layer.
         objectness_loss (dict): Config of objectness loss.

mmdet3d/models/voxel_encoders/pillar_encoder.py

@@ -233,7 +233,7 @@ class DynamicPillarFeatureNet(PillarFeatureNet):
 
         Returns:
             torch.Tensor: Corresponding voxel centers of each points, shape
-                (M, C), where M is the numver of points.
+                (M, C), where M is the number of points.
         """
         # Step 1: scatter voxel into canvas
         # Calculate necessary things for canvas creation

mmdet3d/models/voxel_encoders/voxel_encoder.py

@@ -232,7 +232,7 @@ class DynamicVFE(nn.Module):
             coors (torch.Tensor): Coordinates of voxels, shape is  Nx(1+NDim).
             points (list[torch.Tensor], optional): Raw points used to guide the
                 multi-modality fusion. Defaults to None.
-            img_feats (list[torch.Tensor], optional): Image fetures used for
+            img_feats (list[torch.Tensor], optional): Image features used for
                 multi-modality fusion. Defaults to None.
             img_metas (dict, optional): [description]. Defaults to None.
 
@@ -397,7 +397,7 @@ class HardVFE(nn.Module):
             features (torch.Tensor): Features of voxels, shape is MxNxC.
             num_points (torch.Tensor): Number of points in each voxel.
             coors (torch.Tensor): Coordinates of voxels, shape is Mx(1+NDim).
-            img_feats (list[torch.Tensor], optional): Image fetures used for
+            img_feats (list[torch.Tensor], optional): Image features used for
                 multi-modality fusion. Defaults to None.
             img_metas (dict, optional): [description]. Defaults to None.