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

docs_zh-CN/benchmarks.md

-# 基准测试
\ No newline at end of file
+# 基准测试

docs_zh-CN/changelog.md

-# 变更日志
\ No newline at end of file
+# 变更日志

docs_zh-CN/datasets/nuscenes_det.md

@@ -257,4 +257,3 @@ barrier 0.466   0.581   0.269   0.169   nan     nan
 总的来说，`NuScenesBox` 和我们的 `CameraInstanceBoxes` 的主要区别主要体现在转向角（yaw）定义上。 `NuScenesBox` 定义了一个四元数或三个欧拉角的旋转，而我们的由于实际情况只定义了一个转向角（yaw），它需要我们在预处理和后处理中手动添加一些额外的旋转，例如[这里](https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/datasets/nuscenes_mono_dataset.py#L673)。
 
 另外，请注意，角点和位置的定义在 `NuScenesBox` 中是分离的。例如，在单目 3D 检测中，框位置的定义在其相机坐标中（有关汽车设置，请参阅其官方[插图](https://www.nuscenes.org/nuscenes#data-collection)），即与[我们的](https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/core/bbox/structures/cam_box3d.py)一致。相比之下，它的角点是通过[惯例](https://github.com/nutonomy/nuscenes-devkit/blob/02e9200218977193a1058dd7234f935834378319/python-sdk/nuscenes/utils/data_classes.py#L527) 定义的，“x 向前， y 向左， z 向上”。它导致了与我们的 `CameraInstanceBoxes` 不同的维度和旋转定义理念。一个移除相似冲突的例子是 PR [#744](https://github.com/open-mmlab/mmdetection3d/pull/744)。同样的问题也存在于 LiDAR 系统中。为了解决它们，我们通常会在预处理和后处理中添加一些转换，以保证在整个训练和推理过程中框都在我们的坐标系系统里。
-

docs_zh-CN/supported_tasks/lidar_det3d.md

-# 基于Lidar的3D检测
\ No newline at end of file
+# 基于Lidar的3D检测

docs_zh-CN/supported_tasks/lidar_sem_seg3d.md

-# 基于Lidar的3D语义分割
\ No newline at end of file
+# 基于Lidar的3D语义分割

docs_zh-CN/supported_tasks/vision_det3d.md

-# 基于视觉的3D检测
\ No newline at end of file
+# 基于视觉的3D检测

docs_zh-CN/useful_tools.md

@@ -198,7 +198,7 @@ python tools/model_converters/publish_model.py work_dirs/faster_rcnn/latest.pth
 为了转换 nuImages 数据集为 COCO 格式，请使用下面的指令：
 
 ```shell
-python -u tools/data_converter/nuimage_converter.py --data-root ${DATA_ROOT} --version ${VERIONS} \
+python -u tools/data_converter/nuimage_converter.py --data-root ${DATA_ROOT} --version ${VERSIONS} \
                                                     --out-dir ${OUT_DIR} --nproc ${NUM_WORKERS} --extra-tag ${TAG}
 ```
 

mmdet3d/core/anchor/anchor_3d_generator.py

@@ -99,7 +99,7 @@ class Anchor3DRangeGenerator(object):
             list[torch.Tensor]: Anchors in multiple feature levels.
                 The sizes of each tensor should be [N, 4], where
                 N = width * height * num_base_anchors, width and height
-                are the sizes of the corresponding feature lavel,
+                are the sizes of the corresponding feature level,
                 num_base_anchors is the number of anchors for that level.
         """
         assert self.num_levels == len(featmap_sizes)

mmdet3d/core/bbox/box_np_ops.py

@@ -468,7 +468,7 @@ def rbbox2d_to_near_bbox(rbboxes):
             (N, 5(x, y, xdim, ydim, rad)).
 
     Returns:
-        np.ndarray: Bounding boxes with the shpae of
+        np.ndarray: Bounding boxes with the shape of
             (N, 4(xmin, ymin, xmax, ymax)).
     """
     rots = rbboxes[..., -1]

mmdet3d/core/bbox/coders/smoke_bbox_coder.py

@@ -23,7 +23,7 @@ class SMOKECoder(BaseBBoxCoder):
         self.bbox_code_size = code_size
 
     def encode(self, locations, dimensions, orientations, input_metas):
-        """Encode CameraInstance3DBoxes by locations, dimemsions, orientations.
+        """Encode CameraInstance3DBoxes by locations, dimensions, orientations.
 
         Args:
             locations (Tensor): Center location for 3D boxes.
@@ -55,7 +55,7 @@ class SMOKECoder(BaseBBoxCoder):
                cam2imgs,
                trans_mats,
                locations=None):
-        """Decode regression into locations, dimemsions, orientations.
+        """Decode regression into locations, dimensions, orientations.
 
         Args:
             reg (Tensor): Batch regression for each predict center2d point.
@@ -80,7 +80,7 @@ class SMOKECoder(BaseBBoxCoder):
                 - locations (Tensor): Centers of 3D boxes.
                     shape: (batch * K (max_objs), 3)
                 - dimensions (Tensor): Dimensions of 3D boxes.
-                    shpae: (batch * K (max_objs), 3)
+                    shape: (batch * K (max_objs), 3)
                 - orientations (Tensor): Orientations of 3D
                     boxes.
                     shape: (batch * K (max_objs), 1)
@@ -185,7 +185,7 @@ class SMOKECoder(BaseBBoxCoder):
         rays = torch.atan(locations[:, 0] / (locations[:, 2] + 1e-7))
         alphas = torch.atan(ori_vector[:, 0] / (ori_vector[:, 1] + 1e-7))
 
-        # get cosine value positive and negtive index.
+        # get cosine value positive and negative index.
         cos_pos_inds = (ori_vector[:, 1] >= 0).nonzero()
         cos_neg_inds = (ori_vector[:, 1] < 0).nonzero()
 

mmdet3d/core/bbox/iou_calculators/iou3d_calculator.py

@@ -106,7 +106,7 @@ def bbox_overlaps_nearest_3d(bboxes1,
     Note:
         This function first finds the nearest 2D boxes in bird eye view
         (BEV), and then calculates the 2D IoU using :meth:`bbox_overlaps`.
-        Ths IoU calculator :class:`BboxOverlapsNearest3D` uses this
+        This IoU calculator :class:`BboxOverlapsNearest3D` uses this
         function to calculate IoUs of boxes.
 
         If ``is_aligned`` is ``False``, then it calculates the ious between
@@ -258,7 +258,7 @@ def axis_aligned_bbox_overlaps_3d(bboxes1,
     """
 
     assert mode in ['iou', 'giou'], f'Unsupported mode {mode}'
-    # Either the boxes are empty or the length of boxes's last dimenstion is 6
+    # Either the boxes are empty or the length of boxes's last dimension is 6
     assert (bboxes1.size(-1) == 6 or bboxes1.size(0) == 0)
     assert (bboxes2.size(-1) == 6 or bboxes2.size(0) == 0)
 

mmdet3d/core/bbox/structures/utils.py

@@ -220,7 +220,7 @@ def points_img2cam(points, cam2img):
     Args:
         points (torch.Tensor): 2.5D points in 2D images, [N, 3],
             3 corresponds with x, y in the image and depth.
-        cam2img (torch.Tensor): Camera instrinsic matrix. The shape can be
+        cam2img (torch.Tensor): Camera intrinsic matrix. The shape can be
             [3, 3], [3, 4] or [4, 4].
 
     Returns:
@@ -239,7 +239,7 @@ def points_img2cam(points, cam2img):
     pad_cam2img[:cam2img.shape[0], :cam2img.shape[1]] = cam2img
     inv_pad_cam2img = torch.inverse(pad_cam2img).transpose(0, 1)
 
-    # Do operation in homogenous coordinates.
+    # Do operation in homogeneous coordinates.
     num_points = unnormed_xys.shape[0]
     homo_xys = torch.cat([unnormed_xys, xys.new_ones((num_points, 1))], dim=1)
     points3D = torch.mm(homo_xys, inv_pad_cam2img)[:, :3]

mmdet3d/core/post_processing/box3d_nms.py

@@ -26,7 +26,7 @@ def box3d_multiclass_nms(mlvl_bboxes,
             The coordinate system of the BEV boxes is counterclockwise.
         mlvl_scores (torch.Tensor): Multi-level boxes with shape
             (N, C + 1). N is the number of boxes. C is the number of classes.
-        score_thr (float): Score thredhold to filter boxes with low
+        score_thr (float): Score threshold to filter boxes with low
             confidence.
         max_num (int): Maximum number of boxes will be kept.
         cfg (dict): Configuration dict of NMS.

mmdet3d/core/utils/gaussian.py

@@ -28,7 +28,7 @@ def draw_heatmap_gaussian(heatmap, center, radius, k=1):
     Args:
         heatmap (torch.Tensor): Heatmap to be masked.
         center (torch.Tensor): Center coord of the heatmap.
-        radius (int): Radius of gausian.
+        radius (int): Radius of gaussian.
         K (int, optional): Multiple of masked_gaussian. Defaults to 1.
 
     Returns:

mmdet3d/core/visualizer/open3d_vis.py

@@ -80,10 +80,10 @@ def _draw_bboxes(bbox3d,
             the color of points inside bbox3d. Default: (1, 0, 0).
         rot_axis (int, optional): rotation axis of bbox. Default: 2.
         center_mode (bool, optional): indicate the center of bbox is
-            bottom center or gravity center. avaliable mode
+            bottom center or gravity center. available mode
             ['lidar_bottom', 'camera_bottom']. Default: 'lidar_bottom'.
         mode (str, optional):  indicate type of the input points,
-            avaliable mode ['xyz', 'xyzrgb']. Default: 'xyz'.
+            available mode ['xyz', 'xyzrgb']. Default: 'xyz'.
     """
     if isinstance(bbox3d, torch.Tensor):
         bbox3d = bbox3d.cpu().numpy()
@@ -154,9 +154,9 @@ def show_pts_boxes(points,
             the color of points which are in bbox3d. Default: (1, 0, 0).
         rot_axis (int, optional): rotation axis of bbox. Default: 2.
         center_mode (bool, optional): indicate the center of bbox is bottom
-            center or gravity center. avaliable mode
+            center or gravity center. available mode
             ['lidar_bottom', 'camera_bottom']. Default: 'lidar_bottom'.
-        mode (str, optional):  indicate type of the input points, avaliable
+        mode (str, optional):  indicate type of the input points, available
             mode ['xyz', 'xyzrgb']. Default: 'xyz'.
     """
     # TODO: support score and class info
@@ -215,10 +215,10 @@ def _draw_bboxes_ind(bbox3d,
             the color of points which are in bbox3d. Default: (1, 0, 0).
         rot_axis (int, optional): rotation axis of bbox. Default: 2.
         center_mode (bool, optional): indicate the center of bbox is
-            bottom center or gravity center. avaliable mode
+            bottom center or gravity center. available mode
             ['lidar_bottom', 'camera_bottom']. Default: 'lidar_bottom'.
         mode (str, optional):  indicate type of the input points,
-            avaliable mode ['xyz', 'xyzrgb']. Default: 'xyz'.
+            available mode ['xyz', 'xyzrgb']. Default: 'xyz'.
     """
     if isinstance(bbox3d, torch.Tensor):
         bbox3d = bbox3d.cpu().numpy()
@@ -296,10 +296,10 @@ def show_pts_index_boxes(points,
             the color of points which are in bbox3d. Default: (1, 0, 0).
         rot_axis (int, optional): rotation axis of bbox. Default: 2.
         center_mode (bool, optional): indicate the center of bbox is
-            bottom center or gravity center. avaliable mode
+            bottom center or gravity center. available mode
             ['lidar_bottom', 'camera_bottom']. Default: 'lidar_bottom'.
         mode (str, optional):  indicate type of the input points,
-            avaliable mode ['xyz', 'xyzrgb']. Default: 'xyz'.
+            available mode ['xyz', 'xyzrgb']. Default: 'xyz'.
     """
     # TODO: support score and class info
     assert 0 <= rot_axis <= 2
@@ -353,10 +353,10 @@ class Visualizer(object):
             the color of points which are in bbox3d. Default: (1, 0, 0).
         rot_axis (int, optional): rotation axis of bbox. Default: 2.
         center_mode (bool, optional): indicate the center of bbox is
-            bottom center or gravity center. avaliable mode
+            bottom center or gravity center. available mode
             ['lidar_bottom', 'camera_bottom']. Default: 'lidar_bottom'.
         mode (str, optional):  indicate type of the input points,
-            avaliable mode ['xyz', 'xyzrgb']. Default: 'xyz'.
+            available mode ['xyz', 'xyzrgb']. Default: 'xyz'.
     """
 
     def __init__(self,
@@ -409,9 +409,9 @@ class Visualizer(object):
                 to be visualized. The 3d bbox is in mode of
                 Box3DMode.DEPTH with gravity_center (please refer to
                 core.structures.box_3d_mode).
-            bbox_color (tuple[float]): the color of bbox. Defaule: None.
+            bbox_color (tuple[float]): the color of bbox. Default: None.
             points_in_box_color (tuple[float]): the color of points which
-                are in bbox3d. Defaule: None.
+                are in bbox3d. Default: None.
         """
         if bbox_color is None:
             bbox_color = self.bbox_color

mmdet3d/datasets/kitti_dataset.py

@@ -316,7 +316,7 @@ class KittiDataset(Custom3DDataset):
             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/datasets/kitti_mono_dataset.py

@@ -214,7 +214,7 @@ class KittiMonoDataset(NuScenesMonoDataset):
             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/datasets/lyft_dataset.py

@@ -143,7 +143,7 @@ class LyftDataset(Custom3DDataset):
         """
         info = self.data_infos[index]
 
-        # standard protocal modified from SECOND.Pytorch
+        # standard protocol modified from SECOND.Pytorch
         input_dict = dict(
             sample_idx=info['token'],
             pts_filename=info['lidar_path'],

mmdet3d/datasets/nuscenes_dataset.py

@@ -210,7 +210,7 @@ class NuScenesDataset(Custom3DDataset):
                 - ann_info (dict): Annotation info.
         """
         info = self.data_infos[index]
-        # standard protocal modified from SECOND.Pytorch
+        # standard protocol modified from SECOND.Pytorch
         input_dict = dict(
             sample_idx=info['token'],
             pts_filename=info['lidar_path'],

mmdet3d/datasets/pipelines/loading.py

@@ -49,7 +49,7 @@ class LoadMultiViewImageFromFiles(object):
         if self.to_float32:
             img = img.astype(np.float32)
         results['filename'] = filename
-        # unravel to list, see `DefaultFormatBundle` in formating.py
+        # unravel to list, see `DefaultFormatBundle` in formatting.py
         # which will transpose each image separately and then stack into array
         results['img'] = [img[..., i] for i in range(img.shape[-1])]
         results['img_shape'] = img.shape