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

mmdet3d/ops/ball_query/ball_query.py

@@ -23,7 +23,7 @@ class BallQuery(Function):
             center_xyz (Tensor): (B, npoint, 3) centers of the ball query.
 
         Returns:
-            Tensor: (B, npoint, nsample) tensor with the indicies of
+            Tensor: (B, npoint, nsample) tensor with the indices of
                 the features that form the query balls.
         """
         assert center_xyz.is_contiguous()

mmdet3d/ops/group_points/group_points.py

@@ -183,7 +183,7 @@ class GroupingOperation(Function):
 
         Args:
             features (Tensor): (B, C, N) tensor of features to group.
-            indices (Tensor): (B, npoint, nsample) the indicies of
+            indices (Tensor): (B, npoint, nsample) the indices of
                 features to group with.
 
         Returns:

mmdet3d/ops/knn/knn.py

@@ -27,11 +27,11 @@ class KNN(Function):
             center_xyz (Tensor): (B, npoint, 3) if transposed == False,
                 else (B, 3, npoint). centers of the knn query.
             transposed (bool): whether the input tensors are transposed.
-                defaults to False. Should not expicitly use this keyword
+                defaults to False. Should not explicitly use this keyword
                 when calling knn (=KNN.apply), just add the fourth param.
 
         Returns:
-            Tensor: (B, k, npoint) tensor with the indicies of
+            Tensor: (B, k, npoint) tensor with the indices of
                 the features that form k-nearest neighbours.
         """
         assert k > 0

mmdet3d/ops/norm.py

@@ -26,7 +26,7 @@ class AllReduce(Function):
 
 @NORM_LAYERS.register_module('naiveSyncBN1d')
 class NaiveSyncBatchNorm1d(nn.BatchNorm1d):
-    """Syncronized Batch Normalization for 3D Tensors.
+    """Synchronized Batch Normalization for 3D Tensors.
 
     Note:
         This implementation is modified from
@@ -37,7 +37,7 @@ class NaiveSyncBatchNorm1d(nn.BatchNorm1d):
         when the batch size on each worker is quite different
         (e.g., when scale augmentation is used).
         In 3D detection, different workers has points of different shapes,
-        whish also cause instability.
+        which also cause instability.
 
         Use this implementation before `nn.SyncBatchNorm` is fixed.
         It is slower than `nn.SyncBatchNorm`.
@@ -80,7 +80,7 @@ class NaiveSyncBatchNorm1d(nn.BatchNorm1d):
 
 @NORM_LAYERS.register_module('naiveSyncBN2d')
 class NaiveSyncBatchNorm2d(nn.BatchNorm2d):
-    """Syncronized Batch Normalization for 4D Tensors.
+    """Synchronized Batch Normalization for 4D Tensors.
 
     Note:
         This implementation is modified from

mmdet3d/ops/paconv/paconv.py

@@ -83,7 +83,7 @@ class ScoreNet(nn.Module):
         Args:
             xyz_features (torch.Tensor): (B, C, N, K), features constructed
                 from xyz coordinates of point pairs. May contain relative
-                positions, Euclidian distance, etc.
+                positions, Euclidean distance, etc.
 
         Returns:
             torch.Tensor: (B, N, K, M), predicted scores for `M` kernels.
@@ -174,7 +174,7 @@ class PAConv(nn.Module):
             # (grouped_xyz - center_xyz, grouped_xyz)
             self.scorenet_in_channels = 6
         elif scorenet_input == 'w_neighbor_dist':
-            # (center_xyz, grouped_xyz - center_xyz, Euclidian distance)
+            # (center_xyz, grouped_xyz - center_xyz, Euclidean distance)
             self.scorenet_in_channels = 7
         else:
             raise NotImplementedError(

mmdet3d/ops/paconv/utils.py

@@ -2,14 +2,14 @@ import torch
 
 
 def calc_euclidian_dist(xyz1, xyz2):
-    """Calculate the Euclidian distance between two sets of points.
+    """Calculate the Euclidean distance between two sets of points.
 
     Args:
         xyz1 (torch.Tensor): (N, 3), the first set of points.
         xyz2 (torch.Tensor): (N, 3), the second set of points.
 
     Returns:
-        torch.Tensor: (N, ), the Euclidian distance between each point pair.
+        torch.Tensor: (N, ), the Euclidean distance between each point pair.
     """
     assert xyz1.shape[0] == xyz2.shape[0], 'number of points are not the same'
     assert xyz1.shape[1] == xyz2.shape[1] == 3, \

mmdet3d/ops/pointnet_modules/paconv_sa_module.py

@@ -28,7 +28,7 @@ class PAConvSAModuleMSG(BasePointSAModule):
             - 'w_neighbor': Use xyz coordinates and the difference with center
                 points as input.
             - 'w_neighbor_dist': Use xyz coordinates, the difference with
-                center points and the Euclidian distance as input.
+                center points and the Euclidean distance as input.
 
         scorenet_cfg (dict, optional): Config of the ScoreNet module, which
             may contain the following keys and values:

mmdet3d/ops/spconv/conv.py

@@ -143,16 +143,16 @@ class SparseConvolution(SparseModule):
             out_tensor.indice_dict = input.indice_dict
             out_tensor.grid = input.grid
             return out_tensor
-        datas = input.find_indice_pair(self.indice_key)
+        data = input.find_indice_pair(self.indice_key)
         if self.inverse:
-            assert datas is not None and self.indice_key is not None
-            _, outids, indice_pairs, indice_pair_num, out_spatial_shape = datas
+            assert data is not None and self.indice_key is not None
+            _, outids, indice_pairs, indice_pair_num, out_spatial_shape = data
             assert indice_pairs.shape[0] == np.prod(
                 self.kernel_size
             ), 'inverse conv must have same kernel size as its couple conv'
         else:
-            if self.indice_key is not None and datas is not None:
-                outids, _, indice_pairs, indice_pair_num, _ = datas
+            if self.indice_key is not None and data is not None:
+                outids, _, indice_pairs, indice_pair_num, _ = data
             else:
                 outids, indice_pairs, indice_pair_num = ops.get_indice_pairs(
                     indices,

mmdet3d/ops/spconv/include/prettyprint.h

@@ -93,7 +93,7 @@ struct delimiters {
 };
 
 // Functor to print containers. You can use this directly if you want
-// to specificy a non-default delimiters type. The printing logic can
+// to specify a non-default delimiters type. The printing logic can
 // be customized by specializing the nested template.
 
 template <typename T, typename TChar = char,

mmdet3d/ops/spconv/include/tensorview/tensorview.h

@@ -73,7 +73,7 @@ void sstream_print(SStream &ss, T val, TArgs... args) {
     if (!(expr)) {                                      \
       std::stringstream __macro_s;                      \
       __macro_s << __FILE__ << " " << __LINE__ << "\n"; \
-      __macro_s << #expr << " assert faild. ";          \
+      __macro_s << #expr << " assert failed. ";          \
       tv::sstream_print(__macro_s, __VA_ARGS__);        \
       throw std::runtime_error(__macro_s.str());        \
     }                                                   \
@@ -84,7 +84,7 @@ void sstream_print(SStream &ss, T val, TArgs... args) {
     if (!(expr)) {                                      \
       std::stringstream __macro_s;                      \
       __macro_s << __FILE__ << " " << __LINE__ << "\n"; \
-      __macro_s << #expr << " assert faild. ";          \
+      __macro_s << #expr << " assert failed. ";          \
       tv::sstream_print(__macro_s, __VA_ARGS__);        \
       throw std::invalid_argument(__macro_s.str());     \
     }                                                   \

mmdet3d/ops/voxel/src/voxelization_cuda.cu

@@ -305,7 +305,7 @@ int hard_voxelize_gpu(const at::Tensor& points, at::Tensor& voxels,
   cudaDeviceSynchronize();
   AT_CUDA_CHECK(cudaGetLastError());
 
-  // 3. determin voxel num and voxel's coor index
+  // 3. determine voxel num and voxel's coor index
   // make the logic in the CUDA device could accelerate about 10 times
   auto coor_to_voxelidx = -at::ones(
       {
@@ -316,7 +316,7 @@ int hard_voxelize_gpu(const at::Tensor& points, at::Tensor& voxels,
       {
           1,
       },
-      points.options().dtype(at::kInt));  // must be zero from the begining
+      points.options().dtype(at::kInt));  // must be zero from the beginning
 
   AT_DISPATCH_ALL_TYPES(
       temp_coors.scalar_type(), "determin_duplicate", ([&] {

requirements/runtime.txt

 lyft_dataset_sdk
 networkx>=2.2,<2.3
-# we may unlock the verion of numba in the future
+# we may unlock the version of numba in the future
 numba==0.48.0
 numpy<1.20.0
 nuscenes-devkit

setup.cfg

@@ -11,3 +11,6 @@ known_first_party = mmdet,mmseg,mmdet3d
 known_third_party = cv2,imageio,indoor3d_util,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,pytorch_sphinx_theme,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,tensorflow,terminaltables,torch,trimesh,waymo_open_dataset
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY
+
+[codespell]
+ignore-words-list = ans,refridgerator,crate,hist,formating,dout,wan,nd,fo

tests/data/kitti/kitti_infos_mono3d.coco.json

-{"images": [{"file_name": "training/image_2/000007.png", "id": 7, "Tri2v": [[0.9999976, 0.0007553071, -0.002035826, -0.8086759], [-0.0007854027, 0.9998898, -0.01482298, 0.3195559], [0.002024406, 0.01482454, 0.9998881, -0.7997231], [0.0, 0.0, 0.0, 1.0]], "Trv2c": [[0.007533745, -0.9999714, -0.000616602, -0.004069766], [0.01480249, 0.0007280733, -0.9998902, -0.07631618], [0.9998621, 0.00752379, 0.01480755, -0.2717806], [0.0, 0.0, 0.0, 1.0]], "rect": [[0.9999239, 0.00983776, -0.007445048, 0.0], [-0.009869795, 0.9999421, -0.004278459, 0.0], [0.007402527, 0.004351614, 0.9999631, 0.0], [0.0, 0.0, 0.0, 1.0]], "cam_intrinsic": [[721.5377, 0.0, 609.5593, 44.85728], [0.0, 721.5377, 172.854, 0.2163791], [0.0, 0.0, 1.0, 0.002745884], [0.0, 0.0, 0.0, 1.0]], "width": 1242, "height": 375}], "annotations": [{"file_name": "training/image_2/000007.png", "image_id": 7, "area": 2556.023616260146, "category_name": "Car", "category_id": 2, "bbox": [565.4822720402807, 175.01202566042497, 51.17323679197273, 49.94844525177848], "iscrowd": 0, "bbox_cam3d": [-0.627830982208252, 0.8849999904632568, 25.010000228881836, 3.200000047683716, 1.6100000143051147, 1.659999966621399, -1.590000033378601], "velo_cam3d": -1, "center2d": [591.3814672167642, 198.3730937263457, 25.012745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 2}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 693.1538564468428, "category_name": "Car", "category_id": 2, "bbox": [481.8496708488522, 179.85710612050596, 30.55976691329198, 22.681909139344754], "iscrowd": 0, "bbox_cam3d": [-7.367831230163574, 1.1799999475479126, 47.54999923706055, 3.700000047683716, 1.399999976158142, 1.5099999904632568, 1.5499999523162842], "velo_cam3d": -1, "center2d": [497.72892067550754, 190.75320250122618, 47.552745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 3}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 419.21693566410073, "category_name": "Car", "category_id": 2, "bbox": [542.2247151650495, 175.73341152322814, 23.019633917835904, 18.211277258379255], "iscrowd": 0, "bbox_cam3d": [-4.647830963134766, 0.9800000190734863, 60.52000045776367, 4.050000190734863, 1.4600000381469727, 1.659999966621399, 1.559999942779541], "velo_cam3d": -1, "center2d": [554.1213152040074, 184.53305847203026, 60.522745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 4}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 928.9555081918186, "category_name": "Cyclist", "category_id": 1, "bbox": [330.84191493374504, 176.13804311926262, 24.65593879860404, 37.67674456769879], "iscrowd": 0, "bbox_cam3d": [-12.567831039428711, 1.0199999809265137, 34.09000015258789, 1.9500000476837158, 1.7200000286102295, 0.5, 1.5399999618530273], "velo_cam3d": -1, "center2d": [343.52506265845847, 194.43366972124528, 34.092745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 5}], "categories": [{"id": 0, "name": "Pedestrian"}, {"id": 1, "name": "Cyclist"}, {"id": 2, "name": "Car"}]}
\ No newline at end of file
+{"images": [{"file_name": "training/image_2/000007.png", "id": 7, "Tri2v": [[0.9999976, 0.0007553071, -0.002035826, -0.8086759], [-0.0007854027, 0.9998898, -0.01482298, 0.3195559], [0.002024406, 0.01482454, 0.9998881, -0.7997231], [0.0, 0.0, 0.0, 1.0]], "Trv2c": [[0.007533745, -0.9999714, -0.000616602, -0.004069766], [0.01480249, 0.0007280733, -0.9998902, -0.07631618], [0.9998621, 0.00752379, 0.01480755, -0.2717806], [0.0, 0.0, 0.0, 1.0]], "rect": [[0.9999239, 0.00983776, -0.007445048, 0.0], [-0.009869795, 0.9999421, -0.004278459, 0.0], [0.007402527, 0.004351614, 0.9999631, 0.0], [0.0, 0.0, 0.0, 1.0]], "cam_intrinsic": [[721.5377, 0.0, 609.5593, 44.85728], [0.0, 721.5377, 172.854, 0.2163791], [0.0, 0.0, 1.0, 0.002745884], [0.0, 0.0, 0.0, 1.0]], "width": 1242, "height": 375}], "annotations": [{"file_name": "training/image_2/000007.png", "image_id": 7, "area": 2556.023616260146, "category_name": "Car", "category_id": 2, "bbox": [565.4822720402807, 175.01202566042497, 51.17323679197273, 49.94844525177848], "iscrowd": 0, "bbox_cam3d": [-0.627830982208252, 0.8849999904632568, 25.010000228881836, 3.200000047683716, 1.6100000143051147, 1.659999966621399, -1.590000033378601], "velo_cam3d": -1, "center2d": [591.3814672167642, 198.3730937263457, 25.012745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 2}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 693.1538564468428, "category_name": "Car", "category_id": 2, "bbox": [481.8496708488522, 179.85710612050596, 30.55976691329198, 22.681909139344754], "iscrowd": 0, "bbox_cam3d": [-7.367831230163574, 1.1799999475479126, 47.54999923706055, 3.700000047683716, 1.399999976158142, 1.5099999904632568, 1.5499999523162842], "velo_cam3d": -1, "center2d": [497.72892067550754, 190.75320250122618, 47.552745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 3}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 419.21693566410073, "category_name": "Car", "category_id": 2, "bbox": [542.2247151650495, 175.73341152322814, 23.019633917835904, 18.211277258379255], "iscrowd": 0, "bbox_cam3d": [-4.647830963134766, 0.9800000190734863, 60.52000045776367, 4.050000190734863, 1.4600000381469727, 1.659999966621399, 1.559999942779541], "velo_cam3d": -1, "center2d": [554.1213152040074, 184.53305847203026, 60.522745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 4}, {"file_name": "training/image_2/000007.png", "image_id": 7, "area": 928.9555081918186, "category_name": "Cyclist", "category_id": 1, "bbox": [330.84191493374504, 176.13804311926262, 24.65593879860404, 37.67674456769879], "iscrowd": 0, "bbox_cam3d": [-12.567831039428711, 1.0199999809265137, 34.09000015258789, 1.9500000476837158, 1.7200000286102295, 0.5, 1.5399999618530273], "velo_cam3d": -1, "center2d": [343.52506265845847, 194.43366972124528, 34.092745884], "attribute_name": -1, "attribute_id": -1, "segmentation": [], "id": 5}], "categories": [{"id": 0, "name": "Pedestrian"}, {"id": 1, "name": "Cyclist"}, {"id": 2, "name": "Car"}]}

tests/test_metrics/test_losses.py

@@ -95,7 +95,7 @@ def test_paconv_regularization_loss():
     set_random_seed(0, True)
     model = ToyModel()
 
-    # reduction shoule be in ['none', 'mean', 'sum']
+    # reduction should be in ['none', 'mean', 'sum']
     with pytest.raises(AssertionError):
         paconv_corr_loss = PAConvRegularizationLoss(reduction='l2')
 
@@ -116,7 +116,7 @@ def test_paconv_regularization_loss():
 def test_uncertain_smooth_l1_loss():
     from mmdet3d.models.losses import UncertainL1Loss, UncertainSmoothL1Loss
 
-    # reduction shoule be in ['none', 'mean', 'sum']
+    # reduction should be in ['none', 'mean', 'sum']
     with pytest.raises(AssertionError):
         uncertain_l1_loss = UncertainL1Loss(reduction='l2')
     with pytest.raises(AssertionError):

tests/test_utils/test_box3d.py

@@ -656,7 +656,7 @@ def test_boxes_conversion():
         dtype=torch.float32)
 
     rt_mat = rect @ Trv2c
-    # test coversion with Box type
+    # test conversion with Box type
     cam_to_lidar_box = Box3DMode.convert(camera_boxes, Box3DMode.CAM,
                                          Box3DMode.LIDAR, rt_mat.inverse())
     assert torch.allclose(cam_to_lidar_box.tensor, expected_tensor)

tools/data_converter/kitti_converter.py

@@ -493,7 +493,7 @@ def get_2d_boxes(info, occluded, mono3d=True):
 
 
 def generate_record(ann_rec, x1, y1, x2, y2, sample_data_token, filename):
-    """Generate one 2D annotation record given various informations on top of
+    """Generate one 2D annotation record given various information on top of
     the 2D bounding box coordinates.
 
     Args:
@@ -508,7 +508,7 @@ def generate_record(ann_rec, x1, y1, x2, y2, sample_data_token, filename):
 
     Returns:
         dict: A sample 2D annotation record.
-            - file_name (str): flie name
+            - file_name (str): file name
             - image_id (str): sample data token
             - area (float): 2d box area
             - category_name (str): category name

tools/data_converter/nuscenes_converter.py

@@ -565,7 +565,7 @@ def post_process_coords(
 
 def generate_record(ann_rec: dict, x1: float, y1: float, x2: float, y2: float,
                     sample_data_token: str, filename: str) -> OrderedDict:
-    """Generate one 2D annotation record given various informations on top of
+    """Generate one 2D annotation record given various information on top of
     the 2D bounding box coordinates.
 
     Args:
@@ -580,7 +580,7 @@ def generate_record(ann_rec: dict, x1: float, y1: float, x2: float, y2: float,
 
     Returns:
         dict: A sample 2D annotation record.
-            - file_name (str): flie name
+            - file_name (str): file name
             - image_id (str): sample data token
             - area (float): 2d box area
             - category_name (str): category name