Skip to content

GitLab

Commit 8f88914d authored by liyinhao's avatar liyinhao Committed by zhangwenwei
Browse files

Add docstrings

parent 613c8844
Hide whitespace changes
Inline Side-by-side
Showing with 162 additions and 101 deletions
mmdet3d/datasets/kitti_dataset.py
View file @ 8f88914d
......@@ -339,7 +339,7 @@ class KittiDataset(Custom3DDataset):
class_names,
pklfile_prefix=None,
submission_prefix=None):
"""Convert results to kitti format for evaluation and test submission
"""Convert results to kitti format for evaluation and test submission.
Args:
net_outputs (List[array]): list of array storing the bbox and score
......@@ -348,7 +348,7 @@ class KittiDataset(Custom3DDataset):
submission_prefix (str | None): The prefix of submission file.
Return:
List([dict]): A list of dict have the kitti format
List[dict]: A list of dict have the kitti format
"""
assert len(net_outputs) == len(self.data_infos)
......
mmdet3d/models/dense_heads/anchor3d_head.py
View file @ 8f88914d
......@@ -134,10 +134,10 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Forward function on a single-scale feature map.
Args:
x (Tensor): Input features.
x (torch.Tensor): Input features.
Returns:
tuple[Tensor]: Contain score of each class, bbox predictions
tuple[torch.Tensor]: Contain score of each class, bbox predictions
and class predictions of direction.
"""
cls_score = self.conv_cls(x)
......@@ -151,11 +151,11 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Forward pass.
Args:
feats (list[Tensor]): Multi-level features, e.g.,
feats (list[torch.Tensor]): Multi-level features, e.g.,
features produced by FPN.
Returns:
tuple[list[Tensor]]: Multi-level class score, bbox
tuple[list[torch.Tensor]]: Multi-level class score, bbox
and direction predictions.
"""
return multi_apply(self.forward_single, feats)
......@@ -185,20 +185,21 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Calculate loss of Single-level results.
Args:
cls_score (Tensor): Class score in single-level.
bbox_pred (Tensor): Bbox prediction in single-level.
dir_cls_preds (Tensor): Predictions of direction class
cls_score (torch.Tensor): Class score in single-level.
bbox_pred (torch.Tensor): Bbox prediction in single-level.
dir_cls_preds (torch.Tensor): Predictions of direction class
in single-level.
labels (Tensor): Labels of class.
label_weights (Tensor): Weights of class loss.
bbox_targets (Tensor): Targets of bbox predictions.
bbox_weights (Tensor): Weights of bbox loss.
dir_targets (Tensor): Targets of direction predictions.
dir_weights (Tensor): Weights of direction loss.
labels (torch.Tensor): Labels of class.
label_weights (torch.Tensor): Weights of class loss.
bbox_targets (torch.Tensor): Targets of bbox predictions.
bbox_weights (torch.Tensor): Weights of bbox loss.
dir_targets (torch.Tensor): Targets of direction predictions.
dir_weights (torch.Tensor): Weights of direction loss.
num_total_samples (int): The number of valid samples.
Returns:
tuple[Tensor]: losses of class, bbox and direction, respectively.
tuple[torch.Tensor]: losses of class, bbox
and direction, respectively.
"""
# classification loss
if num_total_samples is None:
......@@ -246,10 +247,10 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Convert the rotation difference to difference in sine function
Args:
boxes1 (Tensor): shape (NxC), where C>=7 and the 7th dimension is
rotation dimension
boxes2 (Tensor): shape (NxC), where C>=7 and the 7th dimension is
rotation dimension
boxes1 (torch.Tensor): shape (NxC), where C>=7 and
the 7th dimension is rotation dimension
boxes2 (torch.Tensor): shape (NxC), where C>=7 and the 7th
dimension is rotation dimension
Returns:
tuple: (boxes1, boxes2) whose 7th dimensions are changed
......@@ -275,15 +276,16 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Calculate losses.
Args:
cls_scores (list[Tensor]): Multi-level class scores.
bbox_preds (list[Tensor]): Multi-level bbox predictions.
dir_cls_preds (list[Tensor]): Multi-level direction
cls_scores (list[torch.Tensor]): Multi-level class scores.
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]): Gt bboxes
of each sample.
gt_labels (list[Tensor]): Gt labels 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[Tensor]): Specify which bounding.
gt_bboxes_ignore (None | list[torch.Tensor]): Specify
which bounding.
Returns:
dict: Contain class, bbox and direction losses of each level.
......@@ -338,13 +340,13 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Get bboxes of anchor head.
Args:
cls_scores (list[Tensor]): Multi-level class scores.
bbox_preds (list[Tensor]): Multi-level bbox predictions.
dir_cls_preds (list[Tensor]): Multi-level direction
cls_scores (list[torch.Tensor]): Multi-level class scores.
bbox_preds (list[torch.Tensor]): Multi-level bbox predictions.
dir_cls_preds (list[torch.Tensor]): Multi-level direction
class predictions.
input_metas (list[dict]): Contain pcd and img's meta info.
cfg (None | ConfigDict): Training or testing config.
rescale (list[Tensor]): whether th rescale bbox.
rescale (list[torch.Tensor]): whether th rescale bbox.
Returns:
list[tuple]: prediction resultes of batches.
......@@ -390,20 +392,21 @@ class Anchor3DHead(nn.Module, AnchorTrainMixin):
"""Get bboxes of single branch.
Args:
cls_scores (Tensor): Class score in single batch.
bbox_preds (Tensor): Bbox prediction in single batch.
dir_cls_preds (Tensor): Predictions of direction class
cls_scores (torch.Tensor): Class score in single batch.
bbox_preds (torch.Tensor): Bbox prediction in single batch.
dir_cls_preds (torch.Tensor): Predictions of direction class
in single batch.
mlvl_anchors (List[torch.Tensor]): Multi-level anchors
in single batch.
mlvl_anchors (List[Tensor]): Multi-level anchors in single batch.
input_meta (list[dict]): Contain pcd and img's meta info.
cfg (None | ConfigDict): Training or testing config.
rescale (list[Tensor]): whether th rescale bbox.
rescale (list[torch.Tensor]): whether th rescale bbox.
Returns:
tuple: Contain predictions of single batch.
- bboxes (:obj:BaseInstance3DBoxes): Predicted 3d bboxes.
- scores (Tensor): Class score of each bbox.
- labels (Tensor): Label of each bbox.
- scores (torch.Tensor): Class score of each bbox.
- labels (torch.Tensor): Label of each bbox.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
......
mmdet3d/models/dense_heads/parta2_rpn_head.py
View file @ 8f88914d
......@@ -109,21 +109,22 @@ class PartA2RPNHead(Anchor3DHead):
"""Get bboxes of single branch.
Args:
cls_scores (Tensor): Class score in single batch.
bbox_preds (Tensor): Bbox prediction in single batch.
dir_cls_preds (Tensor): Predictions of direction class
cls_scores (torch.Tensor): Class score in single batch.
bbox_preds (torch.Tensor): Bbox prediction in single batch.
dir_cls_preds (torch.Tensor): Predictions of direction class
in single batch.
mlvl_anchors (List[torch.Tensor]): Multi-level anchors
in single batch.
mlvl_anchors (List[Tensor]): Multi-level anchors in single batch.
input_meta (list[dict]): Contain pcd and img's meta info.
cfg (None | ConfigDict): Training or testing config.
rescale (list[Tensor]): whether th rescale bbox.
rescale (list[torch.Tensor]): whether th rescale bbox.
Returns:
dict: Predictions of single batch. Contain the keys:
- boxes_3d (:obj:BaseInstance3DBoxes): Predicted 3d bboxes.
- scores_3d (Tensor): Score of each bbox.
- labels_3d (Tensor): Label of each bbox.
- cls_preds (Tensor): Class score of each bbox.
- scores_3d (torch.Tensor): Score of each bbox.
- labels_3d (torch.Tensor): Label of each bbox.
- cls_preds (torch.Tensor): Class score of each bbox.
"""
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
......@@ -198,13 +199,16 @@ class PartA2RPNHead(Anchor3DHead):
"""Class agnostic nms for single batch.
Args:
mlvl_bboxes (Tensor): Bboxes from Multi-level.
mlvl_bboxes_for_nms (Tensor): Bboxes for nms (bev or minmax boxes)
from Multi-level.
mlvl_max_scores (Tensor): Max scores of Multi-level bbox.
mlvl_label_pred (Tensor): Class predictions of Multi-level bbox.
mlvl_cls_score (Tensor): Class scores of Multi-level bbox.
mlvl_dir_scores (Tensor): Direction scores of Multi-level bbox.
mlvl_bboxes (torch.Tensor): Bboxes from Multi-level.
mlvl_bboxes_for_nms (torch.Tensor): Bboxes for nms
(bev or minmax boxes) from Multi-level.
mlvl_max_scores (torch.Tensor): Max scores of Multi-level bbox.
mlvl_label_pred (torch.Tensor): Class predictions
of Multi-level bbox.
mlvl_cls_score (torch.Tensor): Class scores of
Multi-level bbox.
mlvl_dir_scores (torch.Tensor): Direction scores of
Multi-level bbox.
score_thr (int): Score threshold.
max_num (int): Max number of bboxes after nms.
cfg (None | ConfigDict): Training or testing config.
......@@ -213,9 +217,9 @@ class PartA2RPNHead(Anchor3DHead):
Returns:
dict: Predictions of single batch. Contain the keys:
- boxes_3d (:obj:BaseInstance3DBoxes): Predicted 3d bboxes.
- scores_3d (Tensor): Score of each bbox.
- labels_3d (Tensor): Label of each bbox.
- cls_preds (Tensor): Class score of each bbox.
- scores_3d (torch.Tensor): Score of each bbox.
- labels_3d (torch.Tensor): Label of each bbox.
- cls_preds (torch.Tensor): Class score of each bbox.
"""
bboxes = []
scores = []
......
mmdet3d/models/dense_heads/train_mixins.py
View file @ 8f88914d
......@@ -24,7 +24,7 @@ class AnchorTrainMixin(object):
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_labels_list (list[Tensor]): Gt labels of batches.
gt_labels_list (list[torch.Tensor]): Gt labels of batches.
label_channels (int): The channel of labels.
num_classes (int): The number of classes.
sampling (bool): Whether to sample anchors.
......@@ -95,10 +95,10 @@ class AnchorTrainMixin(object):
"""Compute targets of anchors in single batch.
Args:
anchors (Tensor): Concatenated multi-level anchor.
anchors (torch.Tensor): Concatenated multi-level anchor.
gt_bboxes (:obj:BaseInstance3DBoxes): Gt bboxes.
gt_bboxes_ignore (Tensor): Ignored gt bboxes.
gt_labels (Tensor): Gt class labels.
gt_bboxes_ignore (torch.Tensor): Ignored gt bboxes.
gt_labels (torch.Tensor): Gt class labels.
input_meta (dict): Meta info of each image.
label_channels (int): The channel of labels.
num_classes (int): The number of classes.
......@@ -184,10 +184,10 @@ class AnchorTrainMixin(object):
Args:
bbox_assigner (BaseAssigner): assign positive and negative boxes.
anchors (Tensor): Concatenated multi-level anchor.
anchors (torch.Tensor): Concatenated multi-level anchor.
gt_bboxes (:obj:BaseInstance3DBoxes): Gt bboxes.
gt_bboxes_ignore (Tensor): Ignored gt bboxes.
gt_labels (Tensor): Gt class labels.
gt_bboxes_ignore (torch.Tensor): Ignored gt bboxes.
gt_labels (torch.Tensor): Gt class labels.
input_meta (dict): Meta info of each image.
label_channels (int): The channel of labels.
num_classes (int): The number of classes.
......@@ -260,14 +260,14 @@ def get_direction_target(anchors,
"""Encode direction to 0 ~ num_bins-1.
Args:
anchors (Tensor): Concatenated multi-level anchor.
reg_targets (Tensor): Bbox regression targets.
anchors (torch.Tensor): Concatenated multi-level anchor.
reg_targets (torch.Tensor): Bbox regression targets.
dir_offset (int): Direction offset.
num_bins (int): Number of bins to divide 2*PI.
one_hot (bool): Whether to encode as one hot.
Returns:
Tensor: Encoded direction targets.
torch.Tensor: Encoded direction targets.
"""
rot_gt = reg_targets[..., 6] + anchors[..., 6]
offset_rot = box_torch_ops.limit_period(rot_gt - dir_offset, 0, 2 * np.pi)
......
mmdet3d/models/dense_heads/vote_head.py
View file @ 8f88914d
......@@ -188,14 +188,17 @@ class VoteHead(nn.Module):
Args:
bbox_preds (dict): Predictions from forward of vote head.
points (list[Tensor]): Input points.
points (list[torch.Tensor]): Input points.
gt_bboxes_3d (list[:obj:BaseInstance3DBoxes]): Gt bboxes
of each sample.
gt_labels_3d (list[Tensor]): Gt labels of each sample.
pts_semantic_mask (None | list[Tensor]): Point-wise semantic mask.
pts_instance_mask (None | list[Tensor]): Point-wise instance mask.
gt_labels_3d (list[torch.Tensor]): Gt labels of each sample.
pts_semantic_mask (None | list[torch.Tensor]): Point-wise
semantic mask.
pts_instance_mask (None | list[torch.Tensor]): Point-wise
instance mask.
img_metas (list[dict]): Contain pcd and img's meta info.
gt_bboxes_ignore (None | list[Tensor]): Specify which bounding.
gt_bboxes_ignore (None | list[torch.Tensor]): Specify
which bounding.
Returns:
dict: Losses of Votenet.
......@@ -292,15 +295,15 @@ class VoteHead(nn.Module):
"""Generate targets of vote head.
Args:
points (list[Tensor]): Points of each batch.
points (list[torch.Tensor]): Points of each batch.
gt_bboxes_3d (list[:obj:BaseInstance3DBoxes]): gt bboxes of
each batch.
gt_labels_3d (list[Tensor]): gt class labels of each batch.
pts_semantic_mask (None | list[Tensor]): point-wise semantic
gt_labels_3d (list[torch.Tensor]): gt class labels of each batch.
pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
label of each batch.
pts_instance_mask (None | list[Tensor]): point-wise instance
pts_instance_mask (None | list[torch.Tensor]): point-wise instance
label of each batch.
bbox_preds (Tensor): Bbox predictions of vote head.
bbox_preds (torch.Tensor): Bbox predictions of vote head.
Returns:
tuple: Targets of vote head.
......@@ -378,14 +381,14 @@ class VoteHead(nn.Module):
"""Generate targets of vote head for single batch.
Args:
points (Tensor): Points of each batch.
points (torch.Tensor): Points of each batch.
gt_bboxes_3d (:obj:BaseInstance3DBoxes): gt bboxes of each batch.
gt_labels_3d (Tensor): gt class labels of each batch.
pts_semantic_mask (None | Tensor): point-wise semantic
gt_labels_3d (torch.Tensor): gt class labels of each batch.
pts_semantic_mask (None | torch.Tensor): point-wise semantic
label of each batch.
pts_instance_mask (None | Tensor): point-wise instance
pts_instance_mask (None | torch.Tensor): point-wise instance
label of each batch.
aggregated_points (Tensor): Aggregated points from
aggregated_points (torch.Tensor): Aggregated points from
vote aggregation layer.
Returns:
......@@ -491,13 +494,13 @@ class VoteHead(nn.Module):
"""Generate bboxes from vote head predictions.
Args:
points (Tensor): Input points.
points (torch.Tensor): Input points.
bbox_preds (dict): Predictions from vote head.
input_metas (list[dict]): Contain pcd and img's meta info.
rescale (bool): Whether to rescale bboxes.
Returns:
list[tuple[Tensor]]: Contain bbox, scores and labels.
list[tuple[torch.Tensor]]: Contain bbox, scores and labels.
"""
# decode boxes
obj_scores = F.softmax(bbox_preds['obj_scores'], dim=-1)[..., -1]
......@@ -523,14 +526,14 @@ class VoteHead(nn.Module):
"""multi-class nms in single batch.
Args:
obj_scores (Tensor): Objectness score of bboxes.
sem_scores (Tensor): semantic class score of bboxes.
bbox (Tensor): Predicted bbox.
points (Tensor): Input points.
obj_scores (torch.Tensor): Objectness score of bboxes.
sem_scores (torch.Tensor): semantic class score of bboxes.
bbox (torch.Tensor): Predicted bbox.
points (torch.Tensor): Input points.
input_meta (dict): Contain pcd and img's meta info.
Returns:
tuple[Tensor]: Contain bbox, scores and labels.
tuple[torch.Tensor]: Contain bbox, scores and labels.
"""
bbox = input_meta['box_type_3d'](
bbox,
......
mmdet3d/models/detectors/base.py
View file @ 8f88914d
......@@ -7,15 +7,16 @@ class Base3DDetector(BaseDetector):
def forward_test(self, points, img_metas, img=None, **kwargs):
"""
Args:
points (List[Tensor]): the outer list indicates test-time
augmentations and inner Tensor should have a shape NxC,
points (list[torch.Tensor]): the outer list indicates test-time
augmentations and inner torch.Tensor should have a shape NxC,
which contains all points in the batch.
img_metas (List[List[dict]]): the outer list indicates test-time
img_metas (list[list[dict]]): the outer list indicates test-time
augs (multiscale, flip, etc.) and the inner list indicates
images in a batch
img (List[Tensor], optional): the outer list indicates test-time
augmentations and inner Tensor should have a shape NxCxHxW,
which contains all images in the batch. Defaults to None.
img (list[torch.Tensor], optional): the outer
list indicates test-time augmentations and inner
torch.Tensor should have a shape NxCxHxW, which contains
all images in the batch. Defaults to None.
"""
for var, name in [(points, 'points'), (img_metas, 'img_metas')]:
if not isinstance(var, list):
......@@ -42,9 +43,9 @@ class Base3DDetector(BaseDetector):
Calls either forward_train or forward_test depending on whether
return_loss=True. Note this setting will change the expected inputs.
When `return_loss=True`, img and img_metas are single-nested (i.e.
Tensor and List[dict]), and when `resturn_loss=False`, img and
torch.Tensor and list[dict]), and when `resturn_loss=False`, img and
img_metas should be double nested
(i.e. List[Tensor], List[List[dict]]), with the outer list
(i.e. list[torch.Tensor], list[list[dict]]), with the outer list
indicating test time augmentations.
"""
if return_loss:
......
mmdet3d/models/detectors/single_stage.py
View file @ 8f88914d
......@@ -52,7 +52,10 @@ class SingleStage3DDetector(Base3DDetector):
self.bbox_head.init_weights()
def extract_feat(self, points, img_metas=None):
"""Directly extract features from the backbone+neck
"""Directly extract features from the backbone+neck.
Args:
points (torch.Tensor): Input points.
"""
x = self.backbone(points)
if self.with_neck:
......
mmdet3d/models/detectors/votenet.py
View file @ 8f88914d
......@@ -36,15 +36,16 @@ class VoteNet(SingleStage3DDetector):
"""Forward of training.
Args:
points (list[Tensor]): Points of each batch.
points (list[torch.Tensor]): Points of each batch.
img_metas (list): Image metas.
gt_bboxes_3d (:obj:BaseInstance3DBoxes): gt bboxes of each batch.
gt_labels_3d (list[Tensor]): gt class labels of each batch.
pts_semantic_mask (None | list[Tensor]): point-wise semantic
gt_labels_3d (list[torch.Tensor]): gt class labels of each batch.
pts_semantic_mask (None | list[torch.Tensor]): point-wise semantic
label of each batch.
pts_instance_mask (None | list[Tensor]): point-wise instance
pts_instance_mask (None | list[torch.Tensor]): point-wise instance
label of each batch.
gt_bboxes_ignore (None | list[Tensor]): Specify which bounding.
gt_bboxes_ignore (None | list[torch.Tensor]): Specify
which bounding.
Returns:
dict: Losses.
......@@ -63,7 +64,7 @@ class VoteNet(SingleStage3DDetector):
"""Forward of testing.
Args:
points (list[Tensor]): Points of each sample.
points (list[torch.Tensor]): Points of each sample.
img_metas (list): Image metas.
rescale (bool): Whether to rescale results.
......
tools/data_converter/create_gt_database.py
View file @ 8f88914d
......@@ -120,6 +120,27 @@ def create_groundtruth_database(dataset_class_name,
bev_only=False,
coors_range=None,
with_mask=False):
"""Given the raw data, generate the ground truth database.
Args:
dataset_class_name （str): Name of the input dataset.
data_path (str): Path of the data.
info_prefix (str): Prefix of the info file.
info_path (str): Path of the info file.
Default: None.
mask_anno_path (str): Path of the mask_anno.
Default: None.
used_classes (list[str]): Classes have been used.
Default: None.
database_save_path (str): Path to save database.
Default: None.
db_info_save_path (str): Path to save db_info.
Default: None.
relative_path (bool): Whether to use relative path.
Default: True.
with_mask (bool): Whether to use mask.
Default: False.
"""
print(f'Create GT Database of {dataset_class_name}')
dataset_cfg = dict(
type=dataset_class_name,
......
tools/data_converter/kitti_converter.py
View file @ 8f88914d
......@@ -10,6 +10,9 @@ from .kitti_data_utils import get_kitti_image_info
def convert_to_kitti_info_version2(info):
"""convert kitti info v1 to v2 if possible.
Args:
info (dict): Info of the input kitti data.
"""
if 'image' not in info or 'calib' not in info or 'point_cloud' not in info:
info['image'] = {
......@@ -78,6 +81,16 @@ def create_kitti_info_file(data_path,
pkl_prefix='kitti_',
save_path=None,
relative_path=True):
"""Create info file of KITTI dataset.
Given the raw data, generate its related info file in pkl format.
Args:
data_path (str): Path of the data root.
pkl_prefix (str): Prefix of the info file to be generated.
save_path (str): Path to save the info file.
relative_path (bool): Whether to use relative path.
"""
imageset_folder = Path(data_path) / 'ImageSets'
train_img_ids = _read_imageset_file(
str(imageset_folder / 'train_6014.txt'))
......
tools/data_converter/nuscenes_converter.py
View file @ 8f88914d
......@@ -20,6 +20,18 @@ def create_nuscenes_infos(root_path,
info_prefix,
version='v1.0-trainval',
max_sweeps=10):
"""Create info file of nuscene dataset.
Given the raw data, generate its related info file in pkl format.
Args:
root_path (str): Path of the data root.
info_prefix (str): Prefix of the info file to be generated.
version (str): Version of the data.
Default: 'v1.0-trainval'
max_sweeps (int): Max number of sweeps.
Default: 10
"""
from nuscenes.nuscenes import NuScenes
nusc = NuScenes(version=version, dataroot=root_path, verbose=True)
from nuscenes.utils import splits
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment