[Fix]: fix semantic segmentation related bugs (#1909)

delete whitespace

update docs

remove unnecessary optional docs

update docs

add mmengine assertion

add docstring

fix mminstall

update mmengine version

fix

[Fix]: fix semantic segmentation related bugs (#1909)

fix semantic seg

fix lint

remove unused imports

fix

update pointnet2-s3dis config

update data_list according to scene_idxs

remove useless function

fix bug lack `eval_ann_info` during evaluation

fix bug

update doc

fix lint

update docs

Update det3d_dataset.py

update docstrings

update docs

fix lint

update docs

fix

fix

fix lint

configs/_base_/schedules/seg-cosine-100e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=100)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-150e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=150)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=150, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-200e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=200)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/_base_/schedules/seg-cosine-50e.py

@@ -16,8 +16,8 @@ param_scheduler = [
 ]
 
 # runtime settings
-train_cfg = dict(by_epoch=True, max_epochs=50)
-val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1)
+val_cfg = dict()
 test_cfg = dict()
 
 # Default setting for scaling LR automatically

configs/dgcnn/dgcnn_4xb32-cosine-100e_s3dis-seg.py

@@ -16,6 +16,6 @@ model = dict(
         use_normalized_coord=True,
         batch_size=24))
 
-default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2), )
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2))
 train_dataloader = dict(batch_size=32)
-val_cfg = dict(interval=2)
+train_cfg = dict(val_interval=2)

configs/paconv/paconv_ssg-cuda_8xb8-cosine-200e_s3dis-seg.py

@@ -58,5 +58,4 @@ train_pipeline = [
 train_dataloader = dict(batch_size=8, dataset=dict(pipeline=train_pipeline))
 
 # runtime settings
-val_cfg = dict(interval=1)
-train_cfg = dict(by_epoch=True, max_epochs=200)
+train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)

configs/paconv/paconv_ssg_8xb8-cosine-150e_s3dis-seg.py

@@ -56,4 +56,3 @@ train_pipeline = [
 ]
 
 train_dataloader = dict(batch_size=8, dataset=dict(pipeline=train_pipeline))
-val_cfg = dict(interval=1)

configs/pointnet2/pointnet2_msg_2xb16-cosine-250e_scannet-seg-xyz-only.py

@@ -101,7 +101,6 @@ val_dataloader = test_dataloader
 
 # runtime settings
 default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
-val_cfg = dict(interval=5)
 
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-train_cfg = dict(by_epoch=True, max_epochs=250)
+train_cfg = dict(by_epoch=True, max_epochs=250, val_interval=5)

configs/pointnet2/pointnet2_msg_2xb16-cosine-250e_scannet-seg.py

@@ -30,7 +30,6 @@ train_dataloader = dict(batch_size=16)
 
 # runtime settings
 default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
-val_cfg = dict(interval=5)
 
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-train_cfg = dict(by_epoch=True, max_epochs=250)
+train_cfg = dict(by_epoch=True, max_epochs=250, val_interval=5)

configs/pointnet2/pointnet2_msg_2xb16-cosine-80e_s3dis-seg.py

@@ -21,7 +21,6 @@ train_dataloader = dict(batch_size=16)
 
 # runtime settings
 default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2))
-val_cfg = dict(interval=2)
 
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-train_cfg = dict(by_epoch=True, max_epochs=80)
+train_cfg = dict(by_epoch=True, max_epochs=80, val_interval=2)

configs/pointnet2/pointnet2_ssg_2xb16-cosine-200e_scannet-seg-xyz-only.py

@@ -101,4 +101,4 @@ val_dataloader = test_dataloader
 
 # runtime settings
 default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
-val_cfg = dict(interval=5)
+train_cfg = dict(val_interval=5)

configs/pointnet2/pointnet2_ssg_2xb16-cosine-200e_scannet-seg.py

@@ -30,4 +30,4 @@ train_dataloader = dict(batch_size=16)
 
 # runtime settings
 default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
-val_cfg = dict(interval=5)
+train_cfg = dict(val_interval=5)

configs/pointnet2/pointnet2_ssg_2xb16-cosine-50e_s3dis-seg.py

@@ -17,8 +17,8 @@ model = dict(
         batch_size=24))
 
 # data settings
-train_dataloader = dict(batch_size=6)
+train_dataloader = dict(batch_size=16)
 
 # runtime settings
-default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2), )
-val_cfg = dict(interval=2)
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2))
+train_cfg = dict(val_interval=2)

docs/en/notes/faq.md

@@ -10,9 +10,9 @@ We list some potential troubles encountered by users and developers, along with
 
 | MMDetection3D version |     MMEngine version     |      MMCV version       |   MMDetection version    |
 | --------------------- | :----------------------: | :---------------------: | :----------------------: |
-| dev-1.x               | mmengine>=0.1.0, \<0.2.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
-| v1.1.0rc1             | mmengine>=0.1.0, \<0.2.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
-| v1.1.0rc0             | mmengine>=0.1.0, \<0.2.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
+| dev-1.x               | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
+| v1.1.0rc1             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
+| v1.1.0rc0             | mmengine>=0.1.0, \<1.0.0 | mmcv>=2.0.0rc0, \<2.1.0 | mmdet>=3.0.0rc0, \<3.1.0 |
 
 **Note:** If you want to install mmdet3d-v1.0.0x, the compatible MMDetection, MMSegmentation and MMCV versions table can be found at [here](https://mmdetection3d.readthedocs.io/en/latest/faq.html#mmcv-mmdet-mmdet3d-installation). Please choose the correct version of MMCV to avoid installation issues.
 

mmdet3d/__init__.py

 # Copyright (c) OpenMMLab. All rights reserved.
 import mmcv
+import mmengine
+from mmengine.utils import digit_version
 
 import mmdet
-from .version import __version__, short_version
-
-
-def digit_version(version_str):
-    digit_version = []
-    for x in version_str.split('.'):
-        if x.isdigit():
-            digit_version.append(int(x))
-        elif x.find('rc') != -1:
-            patch_version = x.split('rc')
-            digit_version.append(int(patch_version[0]) - 1)
-            digit_version.append(int(patch_version[1]))
-    return digit_version
-
+from .version import __version__, version_info
 
 mmcv_minimum_version = '2.0.0rc0'
 mmcv_maximum_version = '2.1.0'
 mmcv_version = digit_version(mmcv.__version__)
 
+mmengine_minimum_version = '0.1.0'
+mmengine_maximum_version = '1.0.0'
+mmengine_version = digit_version(mmengine.__version__)
+
+mmdet_minimum_version = '3.0.0rc0'
+mmdet_maximum_version = '3.1.0'
+mmdet_version = digit_version(mmdet.__version__)
 
 assert (mmcv_version >= digit_version(mmcv_minimum_version)
         and mmcv_version < digit_version(mmcv_maximum_version)), \
     f'MMCV=={mmcv.__version__} is used but incompatible. ' \
-    f'Please install mmcv>={mmcv_minimum_version}, <={mmcv_maximum_version}.'
+    f'Please install mmcv>={mmcv_minimum_version}, <{mmcv_maximum_version}.'
+
+assert (mmengine_version >= digit_version(mmengine_minimum_version)
+        and mmengine_version < digit_version(mmengine_maximum_version)), \
+    f'MMEngine=={mmengine.__version__} is used but incompatible. ' \
+    f'Please install mmengine>={mmengine_minimum_version}, ' \
+    f'<{mmengine_maximum_version}.'
 
-mmdet_minimum_version = '3.0.0rc0'
-mmdet_maximum_version = '3.1.0'
-mmdet_version = digit_version(mmdet.__version__)
 assert (mmdet_version >= digit_version(mmdet_minimum_version)
         and mmdet_version < digit_version(mmdet_maximum_version)), \
     f'MMDET=={mmdet.__version__} is used but incompatible. ' \
     f'Please install mmdet>={mmdet_minimum_version}, ' \
-    f'<={mmdet_maximum_version}.'
+    f'<{mmdet_maximum_version}.'
 
-__all__ = ['__version__', 'short_version']
+__all__ = ['__version__', 'version_info', 'digit_version']

mmdet3d/datasets/convert_utils.py

@@ -206,11 +206,11 @@ def get_kitti_style_2d_boxes(info: dict,
             0 = fully visible, 1 = partly occluded, 2 = largely occluded,
             3 = unknown, -1 = DontCare.
             Defaults to (0, 1, 2, 3).
-        annos (dict, optional): Original annotations.
+        annos (dict, optional): Original annotations. Defaults to None.
         mono3d (bool): Whether to get boxes with mono3d annotation.
             Defaults to True.
         dataset (str): Dataset name of getting 2d bboxes.
-            Defaults to `kitti`.
+            Defaults to 'kitti'.
 
     Return:
         list[dict]: List of 2d / mono3d annotation record that
@@ -345,9 +345,10 @@ def post_process_coords(
         corner_coords (list[int]): Corner coordinates of reprojected
             bounding box.
         imsize (tuple[int]): Size of the image canvas.
+            Defaults to (1600, 900).
 
     Return:
-        tuple [float]: Intersection of the convex hull of the 2D box
+        tuple[float]: Intersection of the convex hull of the 2D box
             corners and the image canvas.
     """
     polygon_from_2d_box = MultiPoint(corner_coords).convex_hull
@@ -383,10 +384,10 @@ def generate_record(ann_rec: dict, x1: float, y1: float, x2: float, y2: float,
 
     Returns:
         dict: A sample 2d annotation record.
+
             - bbox_label (int): 2d box label id
             - bbox_label_3d (int): 3d box label id
-                - bbox (list[float]): left x, top y, right x, bottom y
-                    of 2d box
+            - bbox (list[float]): left x, top y, right x, bottom y of 2d box
             - bbox_3d_isvalid (bool): whether the box is valid
     """
 
@@ -398,10 +399,6 @@ def generate_record(ann_rec: dict, x1: float, y1: float, x2: float, y2: float,
             cat_name = NuScenesNameMapping[cat_name]
             categories = nus_categories
     else:
-        cat_name = ann_rec['name']
-        if cat_name not in categories:
-            return None
-
         if dataset == 'kitti':
             categories = kitti_categories
         elif dataset == 'waymo':
@@ -409,6 +406,10 @@ def generate_record(ann_rec: dict, x1: float, y1: float, x2: float, y2: float,
         else:
             raise NotImplementedError('Unsupported dataset!')
 
+        cat_name = ann_rec['name']
+        if cat_name not in categories:
+            return None
+
     rec = dict()
     rec['bbox_label'] = categories.index(cat_name)
     rec['bbox_label_3d'] = rec['bbox_label']

mmdet3d/datasets/det3d_dataset.py

 # Copyright (c) OpenMMLab. All rights reserved.
 import copy
 from os import path as osp
-from typing import Callable, List, Optional, Union
+from typing import Callable, List, Optional, Set, Union
 
 import mmengine
 import numpy as np
@@ -28,22 +28,22 @@ class Det3DDataset(BaseDataset):
         ann_file (str): Annotation file path. Defaults to ''.
         metainfo (dict, optional): Meta information for dataset, such as class
             information. Defaults to None.
-        data_prefix (dict, optional): Prefix for training data. Defaults to
+        data_prefix (dict): Prefix for training data. Defaults to
             dict(pts='velodyne', img='').
-        pipeline (list[dict], optional): Pipeline used for data processing.
-            Defaults to None.
-        modality (dict, optional): Modality to specify the sensor data used
-            as input, it usually has following keys:
+        pipeline (list[dict]): Pipeline used for data processing.
+            Defaults to [].
+        modality (dict): Modality to specify the sensor data used as input,
+            it usually has following keys:
 
                 - use_camera: bool
                 - use_lidar: bool
             Defaults to `dict(use_lidar=True, use_camera=False)`
         default_cam_key (str, optional): The default camera name adopted.
             Defaults to None.
-        box_type_3d (str, optional): Type of 3D box of this dataset.
+        box_type_3d (str): Type of 3D box of this dataset.
             Based on the `box_type_3d`, the dataset will encapsulate the box
             to its original format then converted them to `box_type_3d`.
-            Defaults to 'LiDAR'. Available options includes:
+            Defaults to 'LiDAR' in this dataset. Available options includes:
 
             - 'LiDAR': Box in LiDAR coordinates, usually for
               outdoor point cloud 3d detection.
@@ -51,19 +51,20 @@ class Det3DDataset(BaseDataset):
               indoor point cloud 3d detection.
             - 'Camera': Box in camera coordinates, usually
               for vision-based 3d detection.
-
-        filter_empty_gt (bool, optional): Whether to filter the data with
-            empty GT. Defaults to True.
-        test_mode (bool, optional): Whether the dataset is in test mode.
+        filter_empty_gt (bool): Whether to filter the data with empty GT.
+            If it's set to be True, the example with empty annotations after
+            data pipeline will be dropped and a random example will be chosen
+            in `__getitem__`. Defaults to True.
+        test_mode (bool): Whether the dataset is in test mode.
             Defaults to False.
-        load_eval_anns (bool, optional): Whether to load annotations
-            in test_mode, the annotation will be save in `eval_ann_infos`,
-            which can be used in Evaluator. Defaults to True.
-        file_client_args (dict, optional): Configuration of file client.
+        load_eval_anns (bool): Whether to load annotations in test_mode,
+            the annotation will be save in `eval_ann_infos`, which can be
+            used in Evaluator. Defaults to True.
+        file_client_args (dict): Configuration of file client.
             Defaults to dict(backend='disk').
-        show_ins_var (bool, optional): For debug purpose. Whether to show
-            variation of the number of instances before and after through
-            pipeline. Defaults to False.
+        show_ins_var (bool): For debug purpose. Whether to show variation
+            of the number of instances before and after through pipeline.
+            Defaults to False.
     """
 
     def __init__(self,
@@ -154,7 +155,7 @@ class Det3DDataset(BaseDataset):
             f'The number of instances per category in the dataset:\n{table.table}',  # noqa: E501
             'current')
 
-    def _remove_dontcare(self, ann_info):
+    def _remove_dontcare(self, ann_info: dict) -> dict:
         """Remove annotations that do not need to be cared.
 
         -1 indicate dontcare in MMDet3d.
@@ -197,7 +198,7 @@ class Det3DDataset(BaseDataset):
         return ann_info
 
     def parse_ann_info(self, info: dict) -> Optional[dict]:
-        """Process the `instances` in data info to `ann_info`
+        """Process the `instances` in data info to `ann_info`.
 
         In `Custom3DDataset`, we simply concatenate all the field
         in `instances` to `np.ndarray`, you can do the specific
@@ -263,8 +264,8 @@ class Det3DDataset(BaseDataset):
         """Process the raw data info.
 
         Convert all relative path of needed modality data file to
-        the absolute path. And process
-        the `instances` field to `ann_info` in training stage.
+        the absolute path. And process the `instances` field to
+        `ann_info` in training stage.
 
         Args:
             info (dict): Raw info dict.
@@ -392,7 +393,7 @@ class Det3DDataset(BaseDataset):
 
         return example
 
-    def get_cat_ids(self, idx: int) -> List[int]:
+    def get_cat_ids(self, idx: int) -> Set[int]:
         """Get category ids by index. Dataset wrapped by ClassBalancedDataset
         must implement this method.
 

mmdet3d/datasets/kitti_dataset.py

@@ -18,13 +18,13 @@ class KittiDataset(Det3DDataset):
     Args:
         data_root (str): Path of dataset root.
         ann_file (str): Path of annotation file.
-        pipeline (list[dict], optional): Pipeline used for data processing.
-            Defaults to None.
-        modality (dict, optional): Modality to specify the sensor data used
-            as input. Defaults to `dict(use_lidar=True)`.
-        default_cam_key (str, optional): The default camera name adopted.
+        pipeline (list[dict]): Pipeline used for data processing.
+            Defaults to [].
+        modality (dict): Modality to specify the sensor data used as input.
+            Defaults to `dict(use_lidar=True)`.
+        default_cam_key (str): The default camera name adopted.
             Defaults to 'CAM2'.
-        box_type_3d (str, optional): Type of 3D box of this dataset.
+        box_type_3d (str): Type of 3D box of this dataset.
             Based on the `box_type_3d`, the dataset will encapsulate the box
             to its original format then converted them to `box_type_3d`.
             Defaults to 'LiDAR' in this dataset. Available options includes:
@@ -32,12 +32,14 @@ class KittiDataset(Det3DDataset):
             - 'LiDAR': Box in LiDAR coordinates.
             - 'Depth': Box in depth coordinates, usually for indoor dataset.
             - 'Camera': Box in camera coordinates.
-        filter_empty_gt (bool, optional): Whether to filter empty GT.
-            Defaults to True.
-        test_mode (bool, optional): Whether the dataset is in test mode.
+        filter_empty_gt (bool): Whether to filter the data with empty GT.
+            If it's set to be True, the example with empty annotations after
+            data pipeline will be dropped and a random example will be chosen
+            in `__getitem__`. Defaults to True.
+        test_mode (bool): Whether the dataset is in test mode.
             Defaults to False.
-        pcd_limit_range (list[float], optional): The range of point cloud
-            used to filter invalid predicted boxes.
+        pcd_limit_range (list[float]): The range of point cloud used to filter
+            invalid predicted boxes.
             Defaults to [0, -40, -3, 70.4, 40, 0.0].
     """
     # TODO: use full classes of kitti
@@ -119,13 +121,13 @@ class KittiDataset(Det3DDataset):
         return info
 
     def parse_ann_info(self, info: dict) -> dict:
-        """Get annotation info according to the given index.
+        """Process the `instances` in data info to `ann_info`.
 
         Args:
             info (dict): Data information of single data sample.
 
         Returns:
-            dict: annotation information consists of the following keys:
+            dict: Annotation information consists of the following keys:
 
                 - gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`):
                   3D ground truth bboxes.

mmdet3d/datasets/lyft_dataset.py

@@ -21,10 +21,10 @@ class LyftDataset(Det3DDataset):
     Args:
         data_root (str): Path of dataset root.
         ann_file (str): Path of annotation file.
-        pipeline (list[dict], optional): Pipeline used for data processing.
-            Defaults to None.
-        modality (dict, optional): Modality to specify the sensor data used
-            as input. Defaults to dict(use_camera=False, use_lidar=True).
+        pipeline (list[dict]): Pipeline used for data processing.
+            Defaults to [].
+        modality (dict): Modality to specify the sensor data used as input.
+            Defaults to dict(use_camera=False, use_lidar=True).
         box_type_3d (str): Type of 3D box of this dataset.
             Based on the `box_type_3d`, the dataset will encapsulate the box
             to its original format then converted them to `box_type_3d`.
@@ -33,9 +33,11 @@ class LyftDataset(Det3DDataset):
             - 'LiDAR': Box in LiDAR coordinates.
             - 'Depth': Box in depth coordinates, usually for indoor dataset.
             - 'Camera': Box in camera coordinates.
-        filter_empty_gt (bool, optional): Whether to filter empty GT.
-            Defaults to True.
-        test_mode (bool, optional): Whether the dataset is in test mode.
+        filter_empty_gt (bool): Whether to filter the data with empty GT.
+            If it's set to be True, the example with empty annotations after
+            data pipeline will be dropped and a random example will be chosen
+            in `__getitem__`. Defaults to True.
+        test_mode (bool): Whether the dataset is in test mode.
             Defaults to False.
     """
 
@@ -66,13 +68,13 @@ class LyftDataset(Det3DDataset):
             **kwargs)
 
     def parse_ann_info(self, info: dict) -> dict:
-        """Get annotation info according to the given index.
+        """Process the `instances` in data info to `ann_info`.
 
         Args:
             info (dict): Data information of single data sample.
 
         Returns:
-            dict: annotation information consists of the following keys:
+            dict: Annotation information consists of the following keys:
 
                 - gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`):
                   3D ground truth bboxes.

mmdet3d/datasets/nuscenes_dataset.py

@@ -22,9 +22,9 @@ class NuScenesDataset(Det3DDataset):
     Args:
         data_root (str): Path of dataset root.
         ann_file (str): Path of annotation file.
-        task (str, optional): Detection task. Defaults to 'lidar_det'.
-        pipeline (list[dict], optional): Pipeline used for data processing.
-            Defaults to None.
+        task (str): Detection task. Defaults to 'lidar_det'.
+        pipeline (list[dict]): Pipeline used for data processing.
+            Defaults to [].
         box_type_3d (str): Type of 3D box of this dataset.
             Based on the `box_type_3d`, the dataset will encapsulate the box
             to its original format then converted them to `box_type_3d`.
@@ -33,15 +33,17 @@ class NuScenesDataset(Det3DDataset):
             - 'LiDAR': Box in LiDAR coordinates.
             - 'Depth': Box in depth coordinates, usually for indoor dataset.
             - 'Camera': Box in camera coordinates.
-        modality (dict, optional): Modality to specify the sensor data used
-            as input. Defaults to dict(use_camera=False, use_lidar=True).
-        filter_empty_gt (bool, optional): Whether to filter empty GT.
-            Defaults to True.
-        test_mode (bool, optional): Whether the dataset is in test mode.
+        modality (dict): Modality to specify the sensor data used as input.
+            Defaults to dict(use_camera=False, use_lidar=True).
+        filter_empty_gt (bool): Whether to filter the data with empty GT.
+            If it's set to be True, the example with empty annotations after
+            data pipeline will be dropped and a random example will be chosen
+            in `__getitem__`. Defaults to True.
+        test_mode (bool): Whether the dataset is in test mode.
             Defaults to False.
-        with_velocity (bool, optional): Whether to include velocity prediction
+        with_velocity (bool): Whether to include velocity prediction
             into the experiments. Defaults to True.
-        use_valid_flag (bool, optional): Whether to use `use_valid_flag` key
+        use_valid_flag (bool): Whether to use `use_valid_flag` key
             in the info file as mask to filter gt_boxes and gt_names.
             Defaults to False.
     """
@@ -108,13 +110,13 @@ class NuScenesDataset(Det3DDataset):
         return filtered_annotations
 
     def parse_ann_info(self, info: dict) -> dict:
-        """Get annotation info according to the given index.
+        """Process the `instances` in data info to `ann_info`.
 
         Args:
             info (dict): Data information of single data sample.
 
         Returns:
-            dict: annotation information consists of the following keys:
+            dict: Annotation information consists of the following keys:
 
                 - gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`):
                   3D ground truth bboxes.