Skip to content

GitLab

Commit 5d9682a2 authored by zhangwenwei's avatar zhangwenwei
Browse files

Update docstrings

parent 6d189b92
Hide whitespace changes
Inline Side-by-side
Showing with 129 additions and 148 deletions
.gitlab-ci.yml
View file @ 5d9682a2
......@@ -47,7 +47,7 @@ pages:
stage: deploy
script:
- pip install numba==0.48.0
- pip install sphinx sphinx_rtd_theme recommonmark sphinx_markdown_tables
- pip install sphinx sphinx_rtd_theme recommonmark sphinx_markdown_tables m2r
- cd docs
- make html
- cd ..
......
README.md
View file @ 5d9682a2
<div align="center">
<img src="demo/mmdet3d-logo.png" width="600"/>
<img src="resources/mmdet3d-logo.png" width="600"/>
</div>
**News**: We released the codebase v0.1.0.
......
docs/api.rst
View file @ 5d9682a2
......@@ -24,11 +24,6 @@ post_processing
.. automodule:: mmdet3d.core.post_processing
:members:
utils
^^^^^^^^^^
.. automodule:: mmdet3d.core.utils
:members:
mmdet3d.datasets
----------------
......@@ -70,21 +65,6 @@ roi_heads
.. automodule:: mmdet3d.models.roi_heads
:members:
roi_heads.bbox_heads
^^^^^^^^^^^^^^^^^^^^
.. automodule:: mmdet3d.models.roi_heads.bbox_heads
:members:
roi_heads.mask_heads
^^^^^^^^^^^^^^^^^^^^
.. automodule:: mmdet3d.models.roi_heads.mask_heads
:members:
roi_heads.roi_extractors
^^^^^^^^^^^^^^^^^^^^^^^^^
.. automodule:: mmdet3d.models.roi_heads.roi_extractors
:members:
fusion_layers
^^^^^^^^^^^^^
.. automodule:: mmdet3d.models.fusion_layers
......
docs/getting_started.md
View file @ 5d9682a2
......@@ -6,7 +6,7 @@ For installation instructions, please see [install.md](install.md).
## Prepare datasets
It is recommended to symlink the dataset root to `$MMDETECTION3D/data`.
If your folder structure is different, you may need to change the corresponding paths in config files.
If your folder structure is different from the following, you may need to change the corresponding paths in config files.
```
mmdetection3d
......
mmdet3d/core/anchor/anchor_3d_generator.py
View file @ 5d9682a2
......@@ -88,10 +88,10 @@ class Anchor3DRangeGenerator(object):
device (str): Device where the anchors will be put on.
Returns:
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,
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, \
num_base_anchors is the number of anchors for that level.
"""
assert self.num_levels == len(featmap_sizes)
......@@ -168,7 +168,7 @@ class Anchor3DRangeGenerator(object):
device (str): Devices that the anchors will be put on.
Returns:
torch.Tensor: anchors with shape
torch.Tensor: anchors with shape \
[*feature_size, num_sizes, num_rots, 7].
"""
if len(feature_size) == 2:
......@@ -250,11 +250,21 @@ class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
"""Generate anchors in a single range.
Args:
feature_size: list [D, H, W](zyx)
sizes: [N, 3] list of list or array, size of anchors, xyz
feature_size (list[float] | tuple[float]): Feature map size. It is
either a list of a tuple of [D, H, W](in order of z, y, and x).
anchor_range (torch.Tensor | list[float]): Range of anchors with
shape [6]. The order is consistent with that of anchors, i.e.,
(x_min, y_min, z_min, x_max, y_max, z_max).
scale (float | int, optional): The scale factor of anchors.
sizes (list[list] | np.ndarray | torch.Tensor): Anchor size with
shape [N, 3], in order of x, y, z.
rotations (list[float] | np.ndarray | torch.Tensor): Rotations of
anchors in a single feature grid.
device (str): Devices that the anchors will be put on.
Returns:
anchors: [*feature_size, num_sizes, num_rots, 7] tensor.
torch.Tensor: anchors with shape \
[*feature_size, num_sizes, num_rots, 7].
"""
if len(feature_size) == 2:
feature_size = [1, feature_size[0], feature_size[1]]
......@@ -305,12 +315,11 @@ class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
rets.insert(3, sizes)
ret = torch.cat(rets, dim=-1).permute([2, 1, 0, 3, 4, 5])
# [1, 200, 176, N, 2, 7] for kitti after permute
if len(self.custom_values) > 0:
custom_ndim = len(self.custom_values)
custom = ret.new_zeros([*ret.shape[:-1], custom_ndim])
# TODO: check the support of custom values
# custom[:] = self.custom_values
ret = torch.cat([ret, custom], dim=-1)
# [1, 200, 176, N, 2, 9] for nus dataset after permute
return ret
mmdet3d/core/bbox/iou_calculators/iou3d_calculator.py
View file @ 5d9682a2
......@@ -9,7 +9,7 @@ class BboxOverlapsNearest3D(object):
Note:
This IoU calculator first finds the nearest 2D boxes in bird eye view
(BEV), and then calculate the 2D IoU using ``:meth:bbox_overlaps``.
(BEV), and then calculate the 2D IoU using :meth:`bbox_overlaps`.
Args:
coordinate (str): 'camera', 'lidar', or 'depth' coordinate system
......@@ -35,8 +35,8 @@ class BboxOverlapsNearest3D(object):
is_aligned (bool): Whether the calculation is aligned
Return:
torch.Tensor: If ``is_aligned`` is ``True``, return ious between
bboxes1 and bboxes2 with shape (M, N). If ``is_aligned`` is
torch.Tensor: If ``is_aligned`` is ``True``, return ious between \
bboxes1 and bboxes2 with shape (M, N). If ``is_aligned`` is \
``False``, return shape is M.
"""
return bbox_overlaps_nearest_3d(bboxes1, bboxes2, mode, is_aligned,
......@@ -77,7 +77,7 @@ class BboxOverlaps3D(object):
iof (intersection over foreground).
Return:
torch.Tensor: Bbox overlaps results of bboxes1 and bboxes2
torch.Tensor: Bbox overlaps results of bboxes1 and bboxes2 \
with shape (M, N) (aligned mode is not supported currently).
"""
return bbox_overlaps_3d(bboxes1, bboxes2, mode, self.coordinate)
......@@ -114,8 +114,8 @@ def bbox_overlaps_nearest_3d(bboxes1,
is_aligned (bool): Whether the calculation is aligned
Return:
torch.Tensor: If ``is_aligned`` is ``True``, return ious between
bboxes1 and bboxes2 with shape (M, N). If ``is_aligned`` is
torch.Tensor: If ``is_aligned`` is ``True``, return ious between \
bboxes1 and bboxes2 with shape (M, N). If ``is_aligned`` is \
``False``, return shape is M.
"""
assert bboxes1.size(-1) == bboxes2.size(-1) >= 7
......@@ -141,7 +141,7 @@ def bbox_overlaps_3d(bboxes1, bboxes2, mode='iou', coordinate='camera'):
Note:
This function calculate the IoU of 3D boxes based on their volumes.
IoU calculator ``:class:BboxOverlaps3D`` uses this function to
IoU calculator :class:`BboxOverlaps3D` uses this function to
calculate the actual IoUs of boxes.
Args:
......@@ -152,7 +152,7 @@ def bbox_overlaps_3d(bboxes1, bboxes2, mode='iou', coordinate='camera'):
coordinate (str): 'camera' or 'lidar' coordinate system.
Return:
torch.Tensor: Bbox overlaps results of bboxes1 and bboxes2
torch.Tensor: Bbox overlaps results of bboxes1 and bboxes2 \
with shape (M, N) (aligned mode is not supported currently).
"""
assert bboxes1.size(-1) == bboxes2.size(-1) >= 7
......
mmdet3d/core/bbox/structures/base_box3d.py
View file @ 5d9682a2
......@@ -195,11 +195,10 @@ class BaseInstance3DBoxes(object):
In the original implementation of SECOND, checking whether
a box in the range checks whether the points are in a convex
polygon, we try to reduce the burdun for simpler cases.
TODO: check whether this will effect the performance
Returns:
a binary vector, indicating whether each box is inside
the reference range.
torch.Tensor: A binary vector indicating whether each box is \
inside the reference range.
"""
in_range_flags = ((self.tensor[:, 0] > box_range[0])
& (self.tensor[:, 1] > box_range[1])
......@@ -214,8 +213,8 @@ class BaseInstance3DBoxes(object):
"""Check whether the boxes are in the given range.
Args:
box_range (list | torch.Tensor): the range of box
(x_min, y_min, x_max, y_max)
box_range (list | torch.Tensor): The range of box
in order of (x_min, y_min, x_max, y_max).
Returns:
torch.Tensor: Indicating whether each box is inside
......@@ -236,7 +235,7 @@ class BaseInstance3DBoxes(object):
to LiDAR. This requires a transformation matrix.
Returns:
A new object of :class:`xxx` after indexing:
A new object of :class:`BaseInstance3DBoxes` after indexing: \
The converted box of the same type in the `dst` mode.
"""
pass
......@@ -269,7 +268,7 @@ class BaseInstance3DBoxes(object):
threshold (float): The threshold of minimal sizes.
Returns:
torch.Tensor: A binary vector which represents whether each
torch.Tensor: A binary vector which represents whether each \
box is empty (False) or non-empty (True).
"""
box = self.tensor
......@@ -359,7 +358,7 @@ class BaseInstance3DBoxes(object):
"""Clone the Boxes.
Returns:
:obj:`BaseInstance3DBoxes`: Box object with the same properties
:obj:`BaseInstance3DBoxes`: Box object with the same properties \
as self.
"""
original_type = type(self)
......@@ -479,7 +478,7 @@ class BaseInstance3DBoxes(object):
returned Tensor copies.
Returns:
:obj:`BaseInstance3DBoxes`: A new bbox with data and other
:obj:`BaseInstance3DBoxes`: A new bbox with data and other \
properties are similar to self.
"""
new_tensor = self.tensor.new_tensor(data) \
......
mmdet3d/core/bbox/structures/box_3d_mode.py
View file @ 5d9682a2
......@@ -76,7 +76,7 @@ class Box3DMode(IntEnum):
to LiDAR. This requires a transformation matrix.
Returns:
(tuple | list | np.dnarray | torch.Tensor | BaseInstance3DBoxes):
(tuple | list | np.dnarray | torch.Tensor | BaseInstance3DBoxes): \
The converted box of the same type.
"""
if src == dst:
......
mmdet3d/core/bbox/structures/cam_box3d.py
View file @ 5d9682a2
......@@ -100,7 +100,7 @@ class CameraInstance3DBoxes(BaseInstance3DBoxes):
down y
Returns:
torch.Tensor: Corners of each box with size (N, 8, 3)
torch.Tensor: Corners of each box with size (N, 8, 3).
"""
# TODO: rotation_3d_in_axis function do not support
# empty tensor currently.
......@@ -163,8 +163,8 @@ class CameraInstance3DBoxes(BaseInstance3DBoxes):
Defaults to None.
Returns:
tuple or None: When ``points`` is None, the function returns None,
otherwise it returns the rotated points and the
tuple or None: When ``points`` is None, the function returns \
None, otherwise it returns the rotated points and the \
rotation matrix ``rot_mat_T``.
"""
if not isinstance(angle, torch.Tensor):
......@@ -287,7 +287,7 @@ class CameraInstance3DBoxes(BaseInstance3DBoxes):
to LiDAR. This requires a transformation matrix.
Returns:
BaseInstance3DBoxes:
:obj:`BaseInstance3DBoxes`: \
The converted box of the same type in the `dst` mode.
"""
from .box_3d_mode import Box3DMode
......
mmdet3d/core/bbox/structures/depth_box3d.py
View file @ 5d9682a2
......@@ -131,8 +131,8 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
Defaults to None.
Returns:
tuple or None: When ``points`` is None, the function returns None,
otherwise it returns the rotated points and the
tuple or None: When ``points`` is None, the function returns \
None, otherwise it returns the rotated points and the \
rotation matrix ``rot_mat_T``.
"""
if not isinstance(angle, torch.Tensor):
......@@ -207,10 +207,9 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
In the original implementation of SECOND, checking whether
a box in the range checks whether the points are in a convex
polygon, we try to reduce the burdun for simpler cases.
TODO: check whether this will effect the performance
Returns:
torch.Tensor: Indicating whether each box is inside
torch.Tensor: Indicating whether each box is inside \
the reference range.
"""
in_range_flags = ((self.tensor[:, 0] > box_range[0])
......@@ -231,7 +230,7 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
to LiDAR. This requires a transformation matrix.
Returns:
:obj:`BaseInstance3DBoxes`:
:obj:`BaseInstance3DBoxes`: \
The converted box of the same type in the `dst` mode.
"""
from .box_3d_mode import Box3DMode
......
mmdet3d/core/bbox/structures/lidar_box3d.py
View file @ 5d9682a2
......@@ -131,8 +131,8 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
Defaults to None.
Returns:
tuple or None: When ``points`` is None, the function returns None,
otherwise it returns the rotated points and the
tuple or None: When ``points`` is None, the function returns \
None, otherwise it returns the rotated points and the \
rotation matrix ``rot_mat_T``.
"""
if not isinstance(angle, torch.Tensor):
......@@ -204,7 +204,7 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
TODO: check whether this will effect the performance
Returns:
torch.Tensor: Indicating whether each box is inside
torch.Tensor: Indicating whether each box is inside \
the reference range.
"""
in_range_flags = ((self.tensor[:, 0] > box_range[0])
......@@ -225,7 +225,7 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
to LiDAR. This requires a transformation matrix.
Returns:
:obj:`BaseInstance3DBoxes`:
:obj:`BaseInstance3DBoxes`: \
The converted box of the same type in the `dst` mode.
"""
from .box_3d_mode import Box3DMode
......@@ -239,7 +239,7 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
extra_width (float | torch.Tensor): extra width to enlarge the box
Returns:
:obj:`LiDARInstance3DBoxes`: enlarged boxes
:obj:`LiDARInstance3DBoxes`: Enlarged boxes.
"""
enlarged_boxes = self.tensor.clone()
enlarged_boxes[:, 3:6] += extra_width * 2
......@@ -251,7 +251,7 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
"""Find the box which the points are in.
Args:
points (torch.Tensor): Points in shape Nx3
points (torch.Tensor): Points in shape Nx3.
Returns:
torch.Tensor: The index of box where each point are in.
......
mmdet3d/core/bbox/structures/utils.py
View file @ 5d9682a2
......@@ -12,7 +12,7 @@ def limit_period(val, offset=0.5, period=np.pi):
period ([type], optional): Period of the value. Defaults to np.pi.
Returns:
torch.Tensor: value in the range of
torch.Tensor: value in the range of \
[-offset * period, (1-offset) * period]
"""
return val - torch.floor(val / period + offset) * period
......@@ -27,11 +27,11 @@ def rotation_3d_in_axis(points, angles, axis=0):
axis (int, optional): The axis to be rotated. Defaults to 0.
Raises:
ValueError: when the axis is not in range [0, 1, 2], it will
ValueError: when the axis is not in range [0, 1, 2], it will \
raise value error.
Returns:
torch.Tensor: rotated points in shape (N, M, 3)
torch.Tensor: Rotated points in shape (N, M, 3)
"""
rot_sin = torch.sin(angles)
rot_cos = torch.cos(angles)
......
mmdet3d/core/evaluation/lyft_eval.py
View file @ 5d9682a2
......@@ -90,7 +90,7 @@ def lyft_eval(lyft, data_root, res_path, eval_set, output_dir, logger=None):
"""Evaluation API for Lyft dataset.
Args:
lyft (:obj:``LyftDataset``): Lyft class in the sdk.
lyft (:obj:`LyftDataset`): Lyft class in the sdk.
data_root (str): Root of data for reading splits.
res_path (str): Path of result json file recording detections.
eval_set (str): Name of the split for evaluation.
......
mmdet3d/datasets/custom_3d.py
View file @ 5d9682a2
......@@ -84,8 +84,8 @@ class Custom3DDataset(Dataset):
index (int): Index of the sample data to get.
Returns:
dict: Standard input_dict consists of the
data information.
dict: Data information that will be passed to the data \
preprocessing pipelines. It includes the following keys:
- sample_idx (str): sample index
- pts_filename (str): filename of point clouds
......@@ -141,7 +141,7 @@ class Custom3DDataset(Dataset):
index (int): Index for accessing the target data.
Returns:
dict: Training data dict corresponding to the index.
dict: Training data dict of the corresponding index.
"""
input_dict = self.get_data_info(index)
if input_dict is None:
......@@ -160,7 +160,7 @@ class Custom3DDataset(Dataset):
index (int): Index for accessing the target data.
Returns:
dict: Testing data dict corresponding to the index.
dict: Testing data dict of the corresponding index.
"""
input_dict = self.get_data_info(index)
self.pre_pipeline(input_dict)
......@@ -207,9 +207,9 @@ class Custom3DDataset(Dataset):
If not specified, a temp file will be created. Default: None.
Returns:
tuple: (outputs, tmp_dir), outputs is the detection results,
tmp_dir is the temporal directory created for saving json
files when jsonfile_prefix is not specified.
tuple: (outputs, tmp_dir), outputs is the detection results, \
tmp_dir is the temporal directory created for saving json \
files when ``jsonfile_prefix`` is not specified.
"""
if pklfile_prefix is None:
tmp_dir = tempfile.TemporaryDirectory()
......
mmdet3d/datasets/kitti2d_dataset.py
View file @ 5d9682a2
......@@ -80,8 +80,7 @@ class Kitti2DDataset(CustomDataset):
index (int): Index of the annotation data to get.
Returns:
dict: Standard annotation dictionary
consists of the data information.
dict: annotation information consists of the following keys:
- bboxes (np.ndarray): ground truth bboxes
- labels (np.ndarray): labels of ground truths
......
mmdet3d/datasets/kitti_dataset.py
View file @ 5d9682a2
......@@ -15,14 +15,10 @@ from .custom_3d import Custom3DDataset
@DATASETS.register_module()
class KittiDataset(Custom3DDataset):
"""KITTI Dataset.
r"""KITTI Dataset.
This class serves as the API for experiments on the KITTI Dataset.
Please refer to
`<http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d>`_
for data downloading. It is recommended to symlink the dataset root to
$MMDETECTION3D/data and organize them as the doc shows.
This class serves as the API for experiments on the `KITTI Dataset
<http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d>`_.
Args:
data_root (str): Path of dataset root.
......@@ -89,15 +85,15 @@ class KittiDataset(Custom3DDataset):
index (int): Index of the sample data to get.
Returns:
dict: Standard input_dict consists of the
data information.
dict: Data information that will be passed to the data \
preprocessing pipelines. It includes the following keys:
- sample_idx (str): sample index
- pts_filename (str): filename of point clouds
- img_prefix (str | None): prefix of image files
- img_info (dict): image info
- lidar2img (list[np.ndarray], optional): transformations from
lidar to different cameras
- lidar2img (list[np.ndarray], optional): transformations \
from lidar to different cameras
- ann_info (dict): annotation info
"""
info = self.data_infos[index]
......@@ -132,10 +128,9 @@ class KittiDataset(Custom3DDataset):
index (int): Index of the annotation data to get.
Returns:
dict: Standard annotation dictionary
consists of the data information.
dict: annotation information consists of the following keys:
- gt_bboxes_3d (:obj:``LiDARInstance3DBoxes``):
- gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`): \
3D ground truth bboxes
- gt_labels_3d (np.ndarray): labels of ground truths
- gt_bboxes (np.ndarray): 2D ground truth bboxes
......@@ -249,8 +244,8 @@ class KittiDataset(Custom3DDataset):
Default: None.
Returns:
tuple: (result_files, tmp_dir), result_files is a dict containing
the json filepaths, tmp_dir is the temporal directory created
tuple: (result_files, tmp_dir), result_files is a dict containing \
the json filepaths, tmp_dir is the temporal directory created \
for saving json files when jsonfile_prefix is not specified.
"""
if pklfile_prefix is None:
......@@ -458,7 +453,8 @@ class KittiDataset(Custom3DDataset):
class_names,
pklfile_prefix=None,
submission_prefix=None):
"""Convert results to kitti format for evaluation and test submission.
"""Convert 2D detection results to kitti format for evaluation and test
submission.
Args:
net_outputs (list[np.ndarray]): list of array storing the
......
mmdet3d/datasets/lyft_dataset.py
View file @ 5d9682a2
......@@ -22,8 +22,7 @@ class LyftDataset(Custom3DDataset):
Please refer to
`<https://www.kaggle.com/c/3d-object-detection-for-autonomous-vehicles/data>`_ # noqa
for data downloading. It is recommended to symlink the dataset
root to $MMDETECTION3D/data and organize them as the doc shows.
for data downloading.
Args:
ann_file (str): Path of annotation file.
......@@ -127,16 +126,16 @@ class LyftDataset(Custom3DDataset):
index (int): Index of the sample data to get.
Returns:
dict: Standard input_dict consists of the
data information.
dict: Data information that will be passed to the data \
preprocessing pipelines. It includes the following keys:
- sample_idx (str): sample index
- pts_filename (str): filename of point clouds
- sweeps (list[dict]): infos of sweeps
- timestamp (float): sample timestamp
- img_filename (str, optional): image filename
- lidar2img (list[np.ndarray], optional): transformations from
lidar to different cameras
- lidar2img (list[np.ndarray], optional): transformations \
from lidar to different cameras
- ann_info (dict): annotation info
"""
info = self.data_infos[index]
......@@ -186,10 +185,9 @@ class LyftDataset(Custom3DDataset):
index (int): Index of the annotation data to get.
Returns:
dict: Standard annotation dictionary
consists of the data information.
dict: annotation information consists of the following keys:
- gt_bboxes_3d (:obj:``LiDARInstance3DBoxes``):
- gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`): \
3D ground truth bboxes
- gt_labels_3d (np.ndarray): labels of ground truths
- gt_names (list[str]): class names of ground truths
......@@ -320,9 +318,10 @@ class LyftDataset(Custom3DDataset):
the result will not be converted to csv file.
Returns:
tuple (dict, str): result_files is a dict containing the json
filepaths, tmp_dir is the temporal directory created for
saving json files when jsonfile_prefix is not specified.
tuple: Returns (result_files, tmp_dir), where `result_files` is a \
dict containing the json filepaths, `tmp_dir` is the temporal \
directory created for saving json files when \
`jsonfile_prefix` is not specified.
"""
assert isinstance(results, list), 'results must be a list'
assert len(results) == len(self), (
......@@ -472,7 +471,7 @@ def output_to_lyft_box(detection):
detection (dict): Detection results.
Returns:
list[:obj:``LyftBox``]: List of standard LyftBoxes.
list[:obj:`LyftBox`]: List of standard LyftBoxes.
"""
box3d = detection['boxes_3d']
scores = detection['scores_3d'].numpy()
......@@ -504,7 +503,7 @@ def lidar_lyft_box_to_global(info, boxes):
Args:
info (dict): Info for a specific sample data, including the
calibration information.
boxes (list[:obj:``LyftBox``]): List of predicted LyftBoxes.
boxes (list[:obj:`LyftBox`]): List of predicted LyftBoxes.
Returns:
list: List of standard LyftBoxes in the global
......
mmdet3d/datasets/nuscenes_dataset.py
View file @ 5d9682a2
......@@ -17,9 +17,8 @@ class NuScenesDataset(Custom3DDataset):
This class serves as the API for experiments on the NuScenes Dataset.
Please refer to `<https://www.nuscenes.org/download>`_for data
downloading. It is recommended to symlink the dataset root to
$MMDETECTION3D/data and organize them as the doc shows.
Please refer to `NuScenes Dataset <https://www.nuscenes.org/download>`_
for data downloading.
Args:
ann_file (str): Path of annotation file.
......@@ -161,16 +160,16 @@ class NuScenesDataset(Custom3DDataset):
index (int): Index of the sample data to get.
Returns:
dict: Standard input_dict consists of the
data information.
dict: Data information that will be passed to the data \
preprocessing pipelines. It includes the following keys:
- sample_idx (str): sample index
- pts_filename (str): filename of point clouds
- sweeps (list[dict]): infos of sweeps
- timestamp (float): sample timestamp
- img_filename (str, optional): image filename
- lidar2img (list[np.ndarray], optional): transformations from
lidar to different cameras
- lidar2img (list[np.ndarray], optional): transformations \
from lidar to different cameras
- ann_info (dict): annotation info
"""
info = self.data_infos[index]
......@@ -220,10 +219,9 @@ class NuScenesDataset(Custom3DDataset):
index (int): Index of the annotation data to get.
Returns:
dict: Standard annotation dictionary
consists of the data information.
dict: annotation information consists of the following keys:
- gt_bboxes_3d (:obj:``LiDARInstance3DBoxes``):
- gt_bboxes_3d (:obj:`LiDARInstance3DBoxes`): \
3D ground truth bboxes
- gt_labels_3d (np.ndarray): labels of ground truths
- gt_names (list[str]): class names of ground truths
......@@ -392,9 +390,10 @@ class NuScenesDataset(Custom3DDataset):
If not specified, a temp file will be created. Default: None.
Returns:
tuple (dict, str): result_files is a dict containing the json
filepaths, tmp_dir is the temporal directory created for
saving json files when jsonfile_prefix is not specified.
tuple: Returns (result_files, tmp_dir), where `result_files` is a \
dict containing the json filepaths, `tmp_dir` is the temporal \
directory created for saving json files when \
`jsonfile_prefix` is not specified.
"""
assert isinstance(results, list), 'results must be a list'
assert len(results) == len(self), (
......@@ -497,12 +496,12 @@ def output_to_nusc_box(detection):
Args:
detection (dict): Detection results.
- boxes_3d (:obj:``BaseInstance3DBoxes``): detection bbox
- boxes_3d (:obj:`BaseInstance3DBoxes`): detection bbox
- scores_3d (torch.Tensor): detection scores
- labels_3d (torch.Tensor): predicted box labels
Returns:
list[:obj:``NuScenesBox``]: List of standard NuScenesBoxes.
list[:obj:`NuScenesBox`]: List of standard NuScenesBoxes.
"""
box3d = detection['boxes_3d']
scores = detection['scores_3d'].numpy()
......@@ -544,7 +543,7 @@ def lidar_nusc_box_to_global(info,
Args:
info (dict): Info for a specific sample data, including the
calibration information.
boxes (list[:obj:``NuScenesBox``]): List of predicted NuScenesBoxes.
boxes (list[:obj:`NuScenesBox`]): List of predicted NuScenesBoxes.
classes (list[str]): Mapped classes in the evaluation.
eval_configs (object): Evaluation configuration object.
eval_version (str): Evaluation version.
......
mmdet3d/datasets/pipelines/dbsampler.py
View file @ 5d9682a2
......@@ -189,9 +189,9 @@ class DataBaseSampler(object):
Returns:
dict: Dict of sampled 'pseudo ground truths'.
- gt_labels_3d (np.ndarray): labels of ground truths:
labels of sampled ground truths
- gt_bboxes_3d (:obj:`BaseInstance3DBoxes`):
- gt_labels_3d (np.ndarray): ground truths labels \
of sampled objects.
- gt_bboxes_3d (:obj:`BaseInstance3DBoxes`): \
sampled 3D bounding boxes
- points (np.ndarray): sampled points
- group_ids (np.ndarray): ids of sampled ground truths
......
mmdet3d/datasets/pipelines/formating.py
View file @ 5d9682a2
......@@ -22,7 +22,7 @@ class DefaultFormatBundle(object):
- gt_bboxes_ignore: (1)to tensor, (2)to DataContainer
- gt_labels: (1)to tensor, (2)to DataContainer
- gt_masks: (1)to tensor, (2)to DataContainer (cpu_only=True)
- gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor,
- gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor, \
(3)to DataContainer (stack=True)
"""
......@@ -79,25 +79,26 @@ class Collect3D(object):
The "img_meta" item is always populated. The contents of the "img_meta"
dictionary depends on "meta_keys". By default this includes:
- "img_shape": shape of the image input to the network as a tuple
(h, w, c). Note that images may be zero padded on the
- 'img_shape': shape of the image input to the network as a tuple \
(h, w, c). Note that images may be zero padded on the \
bottom/right if the batch tensor is larger than this shape.
- "scale_factor": a float indicating the preprocessing scale
- "flip": a boolean indicating if image flip transform was used
- "filename": path to the image file
- "ori_shape": original shape of the image as a tuple (h, w, c)
- "pad_shape": image shape after padding
- "lidar2img": transform from lidar to image
- 'pcd_horizontal_flip': a boolean indicating if point cloud is
- 'scale_factor': a float indicating the preprocessing scale
- 'flip': a boolean indicating if image flip transform was used
- 'filename': path to the image file
- 'ori_shape': original shape of the image as a tuple (h, w, c)
- 'pad_shape': image shape after padding
- 'lidar2img': transform from lidar to image
- 'pcd_horizontal_flip': a boolean indicating if point cloud is \
flipped horizontally
- 'pcd_vertical_flip': a boolean indicating if point cloud is
- 'pcd_vertical_flip': a boolean indicating if point cloud is \
flipped vertically
- 'box_mode_3d': 3D box mode
- 'box_type_3d': 3D box type
- 'img_norm_cfg': a dict of normalization information:
- mean - per channel mean subtraction
- std - per channel std divisor
- to_rgb - bool indicating if bgr was converted to rgb
- mean: per channel mean subtraction
- std: per channel std divisor
- to_rgb: bool indicating if bgr was converted to rgb
- 'rect': rectification matrix
- 'Trv2c': transformation from velodyne to camera coordinate
- 'P2': transformation betweeen cameras
......@@ -111,11 +112,11 @@ class Collect3D(object):
keys (Sequence[str]): Keys of results to be collected in ``data``.
meta_keys (Sequence[str], optional): Meta keys to be converted to
``mmcv.DataContainer`` and collected in ``data[img_metas]``.
Default: ``('filename', 'ori_shape', 'img_shape', 'lidar2img',
'pad_shape', 'scale_factor', 'flip', 'pcd_horizontal_flip',
'pcd_vertical_flip', 'box_mode_3d', 'box_type_3d', 'img_norm_cfg',
'rect', 'Trv2c', 'P2', 'pcd_trans', 'sample_idx',
'pcd_scale_factor', 'pcd_rotation', 'pts_filename')``
Default: ('filename', 'ori_shape', 'img_shape', 'lidar2img', \
'pad_shape', 'scale_factor', 'flip', 'pcd_horizontal_flip', \
'pcd_vertical_flip', 'box_mode_3d', 'box_type_3d', \
'img_norm_cfg', 'rect', 'Trv2c', 'P2', 'pcd_trans', \
'sample_idx', 'pcd_scale_factor', 'pcd_rotation', 'pts_filename')
"""
def __init__(self,
......
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