Skip to content

GitLab

Commit 21cb2aa6 authored by wangtai's avatar wangtai Committed by zhangwenwei
Browse files

Refine docstrings

parent cfc3f545
Hide whitespace changes
Inline Side-by-side
Showing with 211 additions and 194 deletions
mmdet3d/core/anchor/anchor_3d_generator.py
View file @ 21cb2aa6
......@@ -20,10 +20,10 @@ class Anchor3DRangeGenerator(object):
vary for different anchor sizes if size_per_range is True.
sizes (list[list[float]]): 3D sizes of anchors.
scales (list[int]): Scales of anchors in different feature levels.
rotations (list(float)): Rotations of anchors in a feature grid.
custom_values (tuple(float)): Customized values of that anchor. For
rotations (list[float]): Rotations of anchors in a feature grid.
custom_values (tuple[float]): Customized values of that anchor. For
example, in nuScenes the anchors have velocities.
reshape_out (bool): Whether to reshape the output into (Nx4)
reshape_out (bool): Whether to reshape the output into (N x 4).
size_per_range: Whether to use separate ranges for different sizes.
If size_per_range is True, the ranges should have the same length
as the sizes, if not, it will be duplicated.
......@@ -69,14 +69,14 @@ class Anchor3DRangeGenerator(object):
@property
def num_base_anchors(self):
"""list[int]: total number of base anchors in a feature grid"""
"""list[int]: Total number of base anchors in a feature grid."""
num_rot = len(self.rotations)
num_size = torch.tensor(self.sizes).reshape(-1, 3).size(0)
return num_rot * num_size
@property
def num_levels(self):
"""int: number of feature levels that the generator will be applied"""
"""int: Number of feature levels that the generator is applied."""
return len(self.scales)
def grid_anchors(self, featmap_sizes, device='cuda'):
......@@ -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:
......@@ -226,7 +226,7 @@ class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
according to the feature map sizes.
However, this makes the anchors center does not match the feature grid.
The AlignedAnchor3DRangeGenerator add + 1 when using the feature map sizes
to obtain the corners of the voxel grid. Then it shift the coordinates to
to obtain the corners of the voxel grid. Then it shifts the coordinates to
the center of voxel grid of use the left up corner to distribute anchors.
Args:
......@@ -263,7 +263,7 @@ class AlignedAnchor3DRangeGenerator(Anchor3DRangeGenerator):
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:
......
mmdet3d/core/bbox/box_np_ops.py
View file @ 21cb2aa6
......@@ -58,8 +58,9 @@ def rotation_2d(points, angles):
"""Rotation 2d points based on origin point clockwise when angle positive.
Args:
points (np.ndarray, shape=[N, point_size, 2]): points to be rotated.
angles (np.ndarray, shape=[N]): rotation angle.
points (np.ndarray): Points to be rotated with shape \
(N, point_size, 2).
angles (np.ndarray): Rotation angle with shape (N).
Returns:
np.ndarray: Same shape as points.
......@@ -75,12 +76,12 @@ def center_to_corner_box2d(centers, dims, angles=None, origin=0.5):
format: center(xy), dims(xy), angles(clockwise when positive)
Args:
centers (np.ndarray, shape=[N, 2]): locations in kitti label file.
dims (np.ndarray, shape=[N, 2]): dimensions in kitti label file.
angles (np.ndarray, shape=[N]): rotation_y in kitti label file.
centers (np.ndarray): Locations in kitti label file with shape (N, 2).
dims (np.ndarray): Dimensions in kitti label file with shape (N, 2).
angles (np.ndarray): Rotation_y in kitti label file with shape (N).
Returns:
np.ndarray: Corners with the shape of [N, 4, 2].
np.ndarray: Corners with the shape of (N, 4, 2).
"""
# 'length' in kitti format is in x axis.
# xyz(hwl)(kitti label file)<->xyz(lhw)(camera)<->z(-x)(-y)(wlh)(lidar)
......@@ -146,15 +147,15 @@ def center_to_corner_box3d(centers,
"""Convert kitti locations, dimensions and angles to corners.
Args:
centers (np.ndarray, shape=[N, 3]): Locations in kitti label file.
dims (np.ndarray, shape=[N, 3]): Dimensions in kitti label file.
angles (np.ndarray, shape=[N]): Rotation_y in kitti label file.
centers (np.ndarray): Locations in kitti label file with shape (N, 3).
dims (np.ndarray): Dimensions in kitti label file with shape (N, 3).
angles (np.ndarray): Rotation_y in kitti label file with shape (N).
origin (list or array or float): Origin point relate to smallest point.
use (0.5, 1.0, 0.5) in camera and (0.5, 0.5, 0) in lidar.
axis (int): Rotation axis. 1 for camera and 2 for lidar.
Returns:
np.ndarray: Corners with the shape of [N, 8, 3].
np.ndarray: Corners with the shape of (N, 8, 3).
"""
# 'length' in kitti format is in x axis.
# yzx(hwl)(kitti label file)<->xyz(lhw)(camera)<->z(-x)(-y)(wlh)(lidar)
......@@ -209,11 +210,10 @@ def corner_to_surfaces_3d_jit(corners):
normal vectors all direct to internal.
Args:
corners (np.ndarray, [N, 8, 3]): 3d box corners
with the shape of [N, 8, 3].
corners (np.ndarray): 3d box corners with the shape of (N, 8, 3).
Returns:
np.ndarray: Surfaces with the shape of [N, 6, 4, 3].
np.ndarray: Surfaces with the shape of (N, 6, 4, 3).
"""
# box_corners: [N, 8, 3], must from corner functions in this module
num_boxes = corners.shape[0]
......@@ -275,10 +275,10 @@ def corner_to_surfaces_3d(corners):
normal vectors all direct to internal.
Args:
corners (np.ndarray, [N, 8, 3]): 3d box corners.
corners (np.ndarray): 3D box corners with shape of (N, 8, 3).
Returns:
np.ndarray: Surfaces with the shape of [N, 6, 4, 3].
np.ndarray: Surfaces with the shape of (N, 6, 4, 3).
"""
# box_corners: [N, 8, 3], must from corner functions in this module
surfaces = np.array([
......@@ -320,11 +320,20 @@ def create_anchors_3d_range(feature_size,
dtype=np.float32):
"""
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).
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.
dtype (type): Data type. Default to np.float32.
Returns:
np.ndarray: [*feature_size, num_sizes, num_rots, 7].
np.ndarray: Range based anchors with shape of \
(*feature_size, num_sizes, num_rots, 7).
"""
anchor_range = np.array(anchor_range, dtype)
z_centers = np.linspace(
......@@ -366,11 +375,12 @@ def rbbox2d_to_near_bbox(rbboxes):
"""convert rotated bbox to nearest 'standing' or 'lying' bbox.
Args:
rbboxes (np.ndarray): [N, 5(x, y, xdim, ydim, rad)] rotated bboxes.
rbboxes (np.ndarray): Rotated bboxes with shape of \
(N, 5(x, y, xdim, ydim, rad)).
Returns:
np.ndarray: Bboxes with the shpae of
[N, 4(xmin, ymin, xmax, ymax)].
np.ndarray: Bounding boxes with the shpae of
(N, 4(xmin, ymin, xmax, ymax)).
"""
rots = rbboxes[..., -1]
rots_0_pi_div_2 = np.abs(limit_period(rots, 0.5, np.pi))
......@@ -382,12 +392,12 @@ def rbbox2d_to_near_bbox(rbboxes):
@numba.jit(nopython=True)
def iou_jit(boxes, query_boxes, mode='iou', eps=0.0):
"""Calculate box iou. note that jit version runs ~10x faster than the
"""Calculate box iou. Note that jit version runs ~10x faster than the
box_overlaps function in mmdet3d.core.evaluation.
Args:
boxes (np.ndarray): (N, 4) ndarray of float
query_boxes (np.ndarray): (K, 4) ndarray of float
boxes (np.ndarray): Input bounding boxes with shape of (N, 4).
query_boxes (np.ndarray): Query boxes with shape of (K, 4).
Returns:
np.ndarray: Overlap between boxes and query_boxes
......@@ -515,13 +525,13 @@ def points_in_convex_polygon_3d_jit(points,
"""Check points is in 3d convex polygons.
Args:
points (np.ndarray): [num_points, 3] array.
polygon_surfaces (np.ndarray): [num_polygon, max_num_surfaces,
max_num_points_of_surface, 3]
array. all surfaces' normal vector must direct to internal.
max_num_points_of_surface must at least 3.
num_surfaces (np.ndarray): [num_polygon] array.
indicate how many surfaces a polygon contain
points (np.ndarray): Input points with shape of (num_points, 3).
polygon_surfaces (np.ndarray): Polygon surfaces with shape of \
(num_polygon, max_num_surfaces, max_num_points_of_surface, 3). \
All surfaces' normal vector must direct to internal. \
Max_num_points_of_surface must at least 3.
num_surfaces (np.ndarray): Number of surfaces a polygon contains \
shape of (num_polygon).
Returns:
np.ndarray: Result matrix with the shape of [num_points, num_polygon].
......@@ -595,9 +605,10 @@ def boxes3d_to_corners3d_lidar(boxes3d, bottom_center=True):
2 -------- 1
Args:
boxes3d (np.ndarray): (N, 7) [x, y, z, w, l, h, ry] in LiDAR coords,
see the definition of ry in KITTI dataset
bottom_center (bool): whether z is on the bottom center of object.
boxes3d (np.ndarray): Boxes with shape of (N, 7) \
[x, y, z, w, l, h, ry] in LiDAR coords, see the definition of ry \
in KITTI dataset.
bottom_center (bool): Whether z is on the bottom center of object.
Returns:
np.ndarray: Box corners with the shape of [N, 8, 3].
......
mmdet3d/core/bbox/coders/delta_xyzwhlr_bbox_coder.py
View file @ 21cb2aa6
......@@ -28,7 +28,7 @@ class DeltaXYZWLHRBBoxCoder(BaseBBoxCoder):
ground-truth boxes.
Returns:
torch.Tensor: Box transformation deltas
torch.Tensor: Box transformation deltas.
"""
box_ndim = src_boxes.shape[-1]
cas, cgs, cts = [], [], []
......
mmdet3d/core/bbox/coders/partial_bin_based_bbox_coder.py
View file @ 21cb2aa6
......@@ -28,8 +28,9 @@ class PartialBinBasedBBoxCoder(BaseBBoxCoder):
"""Encode ground truth to prediction targets.
Args:
gt_bboxes_3d (BaseInstance3DBoxes): gt bboxes with shape (n, 7).
gt_labels_3d (torch.Tensor): gt classes.
gt_bboxes_3d (BaseInstance3DBoxes): Ground truth bboxes \
with shape (n, 7).
gt_labels_3d (torch.Tensor): Ground truth classes.
Returns:
tuple: Targets of center, size and direction.
......@@ -58,7 +59,8 @@ class PartialBinBasedBBoxCoder(BaseBBoxCoder):
"""Decode predicted parts to bbox3d.
Args:
bbox_out (dict): predictions from model, should contain keys below
bbox_out (dict): Predictions from model, should contain keys below.
- center: predicted bottom center of bboxes.
- dir_class: predicted bbox direction class.
- dir_res: predicted bbox direction residual.
......@@ -66,7 +68,7 @@ class PartialBinBasedBBoxCoder(BaseBBoxCoder):
- size_res: predicted bbox size residual.
Returns:
torch.Tensor: decoded bbox3d with shape (batch, n, 7)
torch.Tensor: Decoded bbox3d with shape (batch, n, 7).
"""
center = bbox_out['center']
batch_size, num_proposal = center.shape[:2]
......@@ -98,11 +100,11 @@ class PartialBinBasedBBoxCoder(BaseBBoxCoder):
"""Split predicted features to specific parts.
Args:
preds (torch.Tensor): predicted features to split.
base_xyz (torch.Tensor): coordinates of points.
preds (torch.Tensor): Predicted features to split.
base_xyz (torch.Tensor): Coordinates of points.
Returns:
dict[str, torch.Tensor]: split results.
dict[str, torch.Tensor]: Split results.
"""
results = {}
start, end = 0, 0
......@@ -183,7 +185,7 @@ class PartialBinBasedBBoxCoder(BaseBBoxCoder):
limit_period (bool): Whether to limit angle to [-pi, pi].
Returns:
torch.Tensor: angle decoded from angle_cls and angle_res.
torch.Tensor: Angle decoded from angle_cls and angle_res.
"""
angle_per_class = 2 * np.pi / float(self.num_dir_bins)
angle_center = angle_cls.float() * angle_per_class
......
mmdet3d/core/bbox/iou_calculators/iou3d_calculator.py
View file @ 21cb2aa6
......@@ -12,7 +12,7 @@ class BboxOverlapsNearest3D(object):
(BEV), and then calculate the 2D IoU using :meth:`bbox_overlaps`.
Args:
coordinate (str): 'camera', 'lidar', or 'depth' coordinate system
coordinate (str): 'camera', 'lidar', or 'depth' coordinate system.
"""
def __init__(self, coordinate='lidar'):
......@@ -32,7 +32,7 @@ class BboxOverlapsNearest3D(object):
bboxes2 (torch.Tensor): shape (M, 7+N) [x, y, z, h, w, l, ry, v].
mode (str): "iou" (intersection over union) or iof
(intersection over foreground).
is_aligned (bool): Whether the calculation is aligned
is_aligned (bool): Whether the calculation is aligned.
Return:
torch.Tensor: If ``is_aligned`` is ``True``, return ious between \
......@@ -43,7 +43,7 @@ class BboxOverlapsNearest3D(object):
self.coordinate)
def __repr__(self):
"""str: return a string that describes the module"""
"""str: Return a string that describes the module."""
repr_str = self.__class__.__name__
repr_str += f'(coordinate={self.coordinate}'
return repr_str
......@@ -98,8 +98,8 @@ def bbox_overlaps_nearest_3d(bboxes1,
Note:
This function first finds the nearest 2D boxes in bird eye view
(BEV), and then calculate the 2D IoU using ``:meth:bbox_overlaps``.
Ths IoU calculator ``:class:BboxOverlapsNearest3D`` uses this
(BEV), and then calculates the 2D IoU using :meth:`bbox_overlaps`.
Ths IoU calculator :class:`BboxOverlapsNearest3D` uses this
function to calculate IoUs of boxes.
If ``is_aligned`` is ``False``, then it calculates the ious between
......
mmdet3d/core/bbox/samplers/iou_neg_piecewise_sampler.py
View file @ 21cb2aa6
......@@ -14,15 +14,15 @@ class IoUNegPiecewiseSampler(RandomSampler):
by `neg_piece_fractions`.
Args:
num (int): number of proposals.
pos_fraction (float): the fraction of positive proposals.
neg_piece_fractions (list): a list contains fractions that indicates
num (int): Number of proposals.
pos_fraction (float): The fraction of positive proposals.
neg_piece_fractions (list): A list contains fractions that indicates
the ratio of each piece of total negtive samplers.
neg_iou_piece_thrs (list): a list contains IoU thresholds that
neg_iou_piece_thrs (list): A list contains IoU thresholds that
indicate the upper bound of this piece.
neg_pos_ub (float): the total ratio to limit the upper bound
number of negtive samples
add_gt_as_proposals (bool): whether to add gt as proposals.
neg_pos_ub (float): The total ratio to limit the upper bound
number of negtive samples.
add_gt_as_proposals (bool): Whether to add gt as proposals.
"""
def __init__(self,
......@@ -107,9 +107,10 @@ class IoUNegPiecewiseSampler(RandomSampler):
Args:
assign_result (:obj:`AssignResult`): Bbox assigning results.
bboxes (Tensor): Boxes to be sampled from.
gt_bboxes (Tensor): Ground truth bboxes.
gt_labels (Tensor, optional): Class labels of ground truth bboxes.
bboxes (torch.Tensor): Boxes to be sampled from.
gt_bboxes (torch.Tensor): Ground truth bboxes.
gt_labels (torch.Tensor, optional): Class labels of ground truth \
bboxes.
Returns:
:obj:`SamplingResult`: Sampling result.
......
mmdet3d/core/bbox/structures/base_box3d.py
View file @ 21cb2aa6
......@@ -15,7 +15,7 @@ class BaseInstance3DBoxes(object):
Args:
tensor (torch.Tensor | np.ndarray | list): a N x box_dim matrix.
box_dim (int): number of the dimension of a box
box_dim (int): Number of the dimension of a box
Each row is (x, y, z, x_size, y_size, z_size, yaw).
Default to 7.
with_yaw (bool): Whether the box is with yaw rotation.
......@@ -59,10 +59,10 @@ class BaseInstance3DBoxes(object):
@property
def volume(self):
"""Computes the volume of all the boxes.
"""Compute the volume of all the boxes.
Returns:
torch.Tensor: a vector with volume of each box.
torch.Tensor: A vector with volume of each box.
"""
return self.tensor[:, 3] * self.tensor[:, 4] * self.tensor[:, 5]
......@@ -70,10 +70,10 @@ class BaseInstance3DBoxes(object):
def dims(self):
"""Calculate the length in each dimension of all the boxes.
Convert the boxes to the form of (x_size, y_size, z_size)
Convert the boxes to the form of (x_size, y_size, z_size).
Returns:
torch.Tensor: corners of each box with size (N, 8, 3)
torch.Tensor: Corners of each box with size (N, 8, 3).
"""
return self.tensor[:, 3:6]
......@@ -82,7 +82,7 @@ class BaseInstance3DBoxes(object):
"""Obtain the rotation of all the boxes.
Returns:
torch.Tensor: a vector with yaw of each box.
torch.Tensor: A vector with yaw of each box.
"""
return self.tensor[:, 6]
......@@ -91,7 +91,7 @@ class BaseInstance3DBoxes(object):
"""Obtain the height of all the boxes.
Returns:
torch.Tensor: a vector with height of each box.
torch.Tensor: A vector with height of each box.
"""
return self.tensor[:, 5]
......@@ -100,7 +100,7 @@ class BaseInstance3DBoxes(object):
"""Obtain the top height of all the boxes.
Returns:
torch.Tensor: a vector with the top height of each box.
torch.Tensor: A vector with the top height of each box.
"""
return self.bottom_height + self.height
......@@ -109,7 +109,7 @@ class BaseInstance3DBoxes(object):
"""Obtain the bottom's height of all the boxes.
Returns:
torch.Tensor: a vector with bottom's height of each box.
torch.Tensor: A vector with bottom's height of each box.
"""
return self.tensor[:, 2]
......@@ -128,7 +128,7 @@ class BaseInstance3DBoxes(object):
for more clear usage.
Returns:
torch.Tensor: a tensor with center of each box.
torch.Tensor: A tensor with center of each box.
"""
return self.bottom_center
......@@ -137,7 +137,7 @@ class BaseInstance3DBoxes(object):
"""Calculate the bottom center of all the boxes.
Returns:
torch.Tensor: a tensor with center of each box.
torch.Tensor: A tensor with center of each box.
"""
return self.tensor[:, :3]
......@@ -146,7 +146,7 @@ class BaseInstance3DBoxes(object):
"""Calculate the gravity center of all the boxes.
Returns:
torch.Tensor: a tensor with center of each box.
torch.Tensor: A tensor with center of each box.
"""
pass
......@@ -164,8 +164,8 @@ class BaseInstance3DBoxes(object):
"""Calculate whether the points is in any of the boxes.
Args:
angles (float): rotation angles
axis (int): the axis to rotate the boxes
angles (float): Rotation angles
axis (int): The axis to rotate the boxes
"""
pass
......@@ -178,7 +178,7 @@ class BaseInstance3DBoxes(object):
"""Calculate whether the points is in any of the boxes.
Args:
trans_vector (torch.Tensor): translation vector of size 1x3
trans_vector (torch.Tensor): Translation vector of size 1x3.
"""
if not isinstance(trans_vector, torch.Tensor):
trans_vector = self.tensor.new_tensor(trans_vector)
......@@ -194,7 +194,7 @@ class BaseInstance3DBoxes(object):
Note:
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.
polygon, we try to reduce the burden for simpler cases.
Returns:
torch.Tensor: A binary vector indicating whether each box is \
......@@ -227,7 +227,7 @@ class BaseInstance3DBoxes(object):
"""Convert self to `dst` mode.
Args:
dst (:obj:`BoxMode`): the target Box mode
dst (:obj:`BoxMode`): The target Box mode。
rt_mat (np.ndarray | torch.Tensor): The rotation and translation
matrix between different coordinates. Defaults to None.
The conversion from `src` coordinates to `dst` coordinates
......@@ -308,11 +308,11 @@ class BaseInstance3DBoxes(object):
return original_type(b, box_dim=self.box_dim, with_yaw=self.with_yaw)
def __len__(self):
"""int: Number of boxes in the current object"""
"""int: Number of boxes in the current object."""
return self.tensor.shape[0]
def __repr__(self):
"""str: Return a strings that describes the object"""
"""str: Return a strings that describes the object."""
return self.__class__.__name__ + '(\n ' + str(self.tensor) + ')'
@classmethod
......
mmdet3d/core/bbox/structures/cam_box3d.py
View file @ 21cb2aa6
......@@ -228,8 +228,7 @@ class CameraInstance3DBoxes(BaseInstance3DBoxes):
Note:
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
polygon, we try to reduce the burden for simpler cases.
Returns:
torch.Tensor: Indicating whether each box is inside
......
mmdet3d/core/bbox/structures/depth_box3d.py
View file @ 21cb2aa6
......@@ -37,7 +37,7 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
"""Calculate the gravity center of all the boxes.
Returns:
torch.Tensor: a tensor with center of each box.
torch.Tensor: A tensor with center of each box.
"""
bottom_center = self.bottom_center
gravity_center = torch.zeros_like(bottom_center)
......@@ -68,7 +68,7 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
(x1, y0, z0)
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.
......@@ -103,7 +103,7 @@ class DepthInstance3DBoxes(BaseInstance3DBoxes):
"""Calculate the 2D bounding boxes in BEV without rotation.
Returns:
torch.Tensor: a tensor of 2D BEV box of each box.
torch.Tensor: A tensor of 2D BEV box of each box.
"""
# Obtain BEV boxes with rotation in XYWHR format
bev_rotated_boxes = self.bev
......
mmdet3d/core/bbox/structures/lidar_box3d.py
View file @ 21cb2aa6
......@@ -68,7 +68,7 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
(x0, y0, z0)
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.
......@@ -93,8 +93,8 @@ class LiDARInstance3DBoxes(BaseInstance3DBoxes):
"""Calculate the 2D bounding boxes in BEV with rotation.
Returns:
torch.Tensor: A nx5 tensor of 2D BEV box of each box.
The box is in XYWHR format
torch.Tensor: A nx5 tensor of 2D BEV box of each box. \
The box is in XYWHR format.
"""
return self.tensor[:, [0, 1, 3, 4, 6]]
......
mmdet3d/core/bbox/structures/utils.py
View file @ 21cb2aa6
......@@ -7,12 +7,12 @@ def limit_period(val, offset=0.5, period=np.pi):
Args:
val (torch.Tensor): The value to be converted.
offset (float, optional): Offset to set the value range.
offset (float, optional): Offset to set the value range. \
Defaults to 0.5.
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
......@@ -90,7 +90,7 @@ def get_box_type(box_type):
The valid value are "LiDAR", "Camera", or "Depth".
Returns:
tuple: box type and box mode.
tuple: Box type and box mode.
"""
from .box_3d_mode import (Box3DMode, CameraInstance3DBoxes,
DepthInstance3DBoxes, LiDARInstance3DBoxes)
......
mmdet3d/core/bbox/transforms.py
View file @ 21cb2aa6
......@@ -27,7 +27,7 @@ def bbox3d2roi(bbox_list):
"""Convert a list of bboxes to roi format.
Args:
bbox_list (list[torch.Tensor]): a list of bboxes
bbox_list (list[torch.Tensor]): A list of bboxes
corresponding to a batch of images.
Returns:
......@@ -49,9 +49,9 @@ def bbox3d2result(bboxes, scores, labels):
"""Convert detection results to a list of numpy arrays.
Args:
bboxes (torch.Tensor): shape (n, 5)
labels (torch.Tensor): shape (n, )
scores (torch.Tensor): shape (n, )
bboxes (torch.Tensor): Bounding boxes with shape of (n, 5).
labels (torch.Tensor): Labels with shape of (n, ).
scores (torch.Tensor): Scores with shape of (n, ).
Returns:
dict[str, torch.Tensor]: Bbox results in cpu mode.
......
mmdet3d/core/evaluation/indoor_eval.py
View file @ 21cb2aa6
......@@ -8,14 +8,16 @@ def average_precision(recalls, precisions, mode='area'):
"""Calculate average precision (for single or multiple scales).
Args:
recalls (np.ndarray): shape (num_scales, num_dets) or (num_dets, )
precisions (np.ndarray): shape (num_scales, num_dets) or (num_dets, )
recalls (np.ndarray): Recalls with shape of (num_scales, num_dets) \
or (num_dets, ).
precisions (np.ndarray): Precisions with shape of \
(num_scales, num_dets) or (num_dets, ).
mode (str): 'area' or '11points', 'area' means calculating the area
under precision-recall curve, '11points' means calculating
the average precision of recalls at [0, 0.1, ..., 1]
Returns:
float or np.ndarray: calculated average precision
float or np.ndarray: Calculated average precision.
"""
if recalls.ndim == 1:
recalls = recalls[np.newaxis, :]
......@@ -55,14 +57,14 @@ def eval_det_cls(pred, gt, iou_thr=None):
single class.
Args:
pred (dict): {img_id: [(bbox, score)]} where bbox is numpy array.
gt (dict): {img_id: [bbox]}.
iou_thr (list[float]): a list, iou threshold.
pred (dict): Predictions mapping from image id to bounding boxes \
and scores.
gt (dict): Ground truths mapping from image id to bounding boxes.
iou_thr (list[float]): A list of iou thresholds.
Return:
np.ndarray: numpy array of length nd.
np.ndarray: numpy array of length nd.
float: scalar, average precision.
tuple (np.ndarray, np.ndarray, float): Recalls, precisions and \
average precision.
"""
# {img_id: {'bbox': box structure, 'det': matched list}}
......@@ -167,7 +169,8 @@ def eval_map_recall(pred, gt, ovthresh=None):
Args:
pred (dict): Information of detection results,
which maps class_id and predictions.
gt (dict): information of gt results, which maps class_id and gt.
gt (dict): Information of ground truths, which maps class_id and \
ground truths.
ovthresh (list[float]): iou threshold.
Default: None.
......@@ -213,7 +216,7 @@ def indoor_eval(gt_annos,
dt_annos (list[dict]): Detection annotations. the dict
includes the following keys
- labels_3d (torch.Tensor): Labels of boxes.
- boxes_3d (BaseInstance3DBoxes): 3d bboxes in Depth coordinate.
- boxes_3d (BaseInstance3DBoxes): 3D bboxes in Depth coordinate.
- scores_3d (torch.Tensor): Scores of boxes.
metric (list[float]): AP IoU thresholds.
label2cat (dict): {label: cat}.
......
mmdet3d/core/evaluation/lyft_eval.py
View file @ 21cb2aa6
......@@ -142,6 +142,7 @@ def get_classwise_aps(gt, predictions, class_names, iou_thresholds):
"""Returns an array with an average precision per class.
Note: Ground truth and predictions should have the following format.
.. code-block::
gt = [{
......@@ -200,13 +201,13 @@ def get_single_class_aps(gt, predictions, iou_thresholds):
Args:
gt (list[dict]): list of dictionaries in the format described above.
predictions (list[dict]): list of dictionaries in the format
predictions (list[dict]): list of dictionaries in the format \
described below.
iou_thresholds (list[float]): IOU thresholds used to calculate
iou_thresholds (list[float]): IOU thresholds used to calculate \
TP / FN
Returns:
tuple[np.ndarray]: returns (recalls, precisions, average precisions)
tuple[np.ndarray]: Returns (recalls, precisions, average precisions)
for each class.
"""
num_gts = len(gt)
......
mmdet3d/core/post_processing/merge_augs.py
View file @ 21cb2aa6
......@@ -10,18 +10,18 @@ def merge_aug_bboxes_3d(aug_results, img_metas, test_cfg):
Args:
aug_results (list[dict]): The dict of detection results.
The dict contains the following keys
- boxes_3d (:obj:`BaseInstance3DBoxes`): detection bbox
- scores_3d (torch.Tensor): detection scores
- labels_3d (torch.Tensor): predicted box labels
img_metas (list[dict]): Meta information of each sample
- boxes_3d (:obj:`BaseInstance3DBoxes`): Detection bbox.
- scores_3d (torch.Tensor): Detection scores.
- labels_3d (torch.Tensor): Predicted box labels.
img_metas (list[dict]): Meta information of each sample.
test_cfg (dict): Test config.
Returns:
dict: bbox results in cpu mode, containing the merged results
dict: Bounding boxes results in cpu mode, containing merged results.
- boxes_3d (:obj:`BaseInstance3DBoxes`): merged detection bbox
- scores_3d (torch.Tensor): merged detection scores
- labels_3d (torch.Tensor): merged predicted box labels
- boxes_3d (:obj:`BaseInstance3DBoxes`): Merged detection bbox.
- scores_3d (torch.Tensor): Merged detection scores.
- labels_3d (torch.Tensor): Merged predicted box labels.
"""
assert len(aug_results) == len(img_metas), \
......
mmdet3d/core/voxel/voxel_generator.py
View file @ 21cb2aa6
......@@ -40,22 +40,22 @@ class VoxelGenerator(object):
@property
def voxel_size(self):
"""list[float]: size of a single voxel"""
"""list[float]: Size of a single voxel."""
return self._voxel_size
@property
def max_num_points_per_voxel(self):
"""int: maximum number of points per voxel"""
"""int: Maximum number of points per voxel."""
return self._max_num_points
@property
def point_cloud_range(self):
"""list[float]: range of point cloud"""
"""list[float]: Range of point cloud."""
return self._point_cloud_range
@property
def grid_size(self):
"""np.ndarray: The size of grids"""
"""np.ndarray: The size of grids."""
return self._grid_size
......@@ -68,18 +68,18 @@ def points_to_voxel(points,
"""convert kitti points(N, >=3) to voxels.
Args:
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and \
points[:, 3:] contain other information such as reflectivity.
voxel_size (list, tuple, np.ndarray): [3] xyz, indicate voxel size
coors_range (list[float | tuple[float] | ndarray]): Voxel range.
coors_range (list[float | tuple[float] | ndarray]): Voxel range. \
format: xyzxyz, minmax
max_points (int): Indicate maximum points contained in a voxel.
reverse_index (bool): Whether return reversed coordinates.
if points has xyz format and reverse_index is True, output
coordinates will be zyx format, but points in features always
reverse_index (bool): Whether return reversed coordinates. \
if points has xyz format and reverse_index is True, output \
coordinates will be zyx format, but points in features always \
xyz format.
max_voxels (int): Maximum number of voxels this function create.
for second, 20000 is a good choice. Points should be shuffled for
max_voxels (int): Maximum number of voxels this function creates. \
For second, 20000 is a good choice. Points should be shuffled for \
randomness before this function because max_voxels drops points.
Returns:
......@@ -133,20 +133,20 @@ def _points_to_voxel_reverse_kernel(points,
"""convert kitti points(N, >=3) to voxels.
Args:
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and \
points[:, 3:] contain other information such as reflectivity.
voxel_size (list, tuple, np.ndarray): [3] xyz, indicate voxel size
coors_range (list[float | tuple[float] | ndarray]): Range of voxels.
voxel_size (list, tuple, np.ndarray): [3] xyz, indicate voxel size \
coors_range (list[float | tuple[float] | ndarray]): Range of voxels. \
format: xyzxyz, minmax
num_points_per_voxel (int): Number of points per voxel.
coor_to_voxel_idx (np.ndarray): A voxel grid of shape (D, H, W), which
has the same shape as the complete voxel map. It indicates the
index of each corresponding voxel.
coor_to_voxel_idx (np.ndarray): A voxel grid of shape (D, H, W), \
which has the same shape as the complete voxel map. It indicates \
the index of each corresponding voxel.
voxels (np.ndarray): Created empty voxels.
coors (np.ndarray): Created coordinates of each voxel.
max_points (int): Indicate maximum points contained in a voxel.
max_voxels (int): Maximum number of voxels this function create.
for second, 20000 is a good choice. Points should be shuffled for
max_voxels (int): Maximum number of voxels this function create. \
for second, 20000 is a good choice. Points should be shuffled for \
randomness before this function because max_voxels drops points.
Returns:
......@@ -207,20 +207,20 @@ def _points_to_voxel_kernel(points,
"""convert kitti points(N, >=3) to voxels.
Args:
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and
points (np.ndarray): [N, ndim]. points[:, :3] contain xyz points and \
points[:, 3:] contain other information such as reflectivity.
voxel_size (list, tuple, np.ndarray): [3] xyz, indicate voxel size
coors_range (list[float | tuple[float] | ndarray]): Range of voxels.
voxel_size (list, tuple, np.ndarray): [3] xyz, indicate voxel size.
coors_range (list[float | tuple[float] | ndarray]): Range of voxels. \
format: xyzxyz, minmax
num_points_per_voxel (int): Number of points per voxel.
coor_to_voxel_idx (np.ndarray): A voxel grid of shape (D, H, W), which
has the same shape as the complete voxel map. It indicates the
index of each corresponding voxel.
coor_to_voxel_idx (np.ndarray): A voxel grid of shape (D, H, W), \
which has the same shape as the complete voxel map. It indicates \
the index of each corresponding voxel.
voxels (np.ndarray): Created empty voxels.
coors (np.ndarray): Created coordinates of each voxel.
max_points (int): Indicate maximum points contained in a voxel.
max_voxels (int): Maximum number of voxels this function create.
for second, 20000 is a good choice. Points should be shuffled for
max_voxels (int): Maximum number of voxels this function create. \
for second, 20000 is a good choice. Points should be shuffled for \
randomness before this function because max_voxels drops points.
Returns:
......
mmdet3d/datasets/custom_3d.py
View file @ 21cb2aa6
......@@ -30,9 +30,9 @@ class Custom3DDataset(Dataset):
to its original format then converted them to `box_type_3d`.
Defaults to 'LiDAR'. Available options includes
- 'LiDAR': box in LiDAR coordinates
- 'Depth': box in depth coordinates, usually for indoor dataset
- 'Camera': box in camera coordinates
- '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.
......@@ -87,10 +87,10 @@ class Custom3DDataset(Dataset):
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
- file_name (str): filename of point clouds
- ann_info (dict): annotation info
- sample_idx (str): Sample index.
- pts_filename (str): Filename of point clouds.
- file_name (str): Filename of point clouds.
- ann_info (dict): Annotation info.
"""
info = self.data_infos[index]
sample_idx = info['point_cloud']['lidar_idx']
......@@ -114,15 +114,15 @@ class Custom3DDataset(Dataset):
Args:
results (dict): Dict before data preprocessing.
- img_fields (list): image fields
- bbox3d_fields (list): 3D bounding boxes fields
- pts_mask_fields (list): mask fields of points
- pts_seg_fields (list): mask fields of point segments
- bbox_fields (list): fields of bounding boxes
- mask_fields (list): fields of masks
- seg_fields (list): segment fields
- box_type_3d (str): 3D box type
- box_mode_3d (str): 3D box mode
- img_fields (list): Image fields.
- bbox3d_fields (list): 3D bounding boxes fields.
- pts_mask_fields (list): Mask fields of points.
- pts_seg_fields (list): Mask fields of point segments.
- bbox_fields (list): Fields of bounding boxes.
- mask_fields (list): Fields of masks.
- seg_fields (list): Segment fields.
- box_type_3d (str): 3D box type.
- box_mode_3d (str): 3D box mode.
"""
results['img_fields'] = []
results['bbox3d_fields'] = []
......@@ -179,7 +179,7 @@ class Custom3DDataset(Dataset):
a tuple or list, override the CLASSES defined by the dataset.
Return:
list[str]: return the list of class names
list[str]: A list of class names.
"""
if classes is None:
return cls.CLASSES
......
mmdet3d/datasets/kitti2d_dataset.py
View file @ 21cb2aa6
......@@ -80,10 +80,10 @@ class Kitti2DDataset(CustomDataset):
index (int): Index of the annotation data to get.
Returns:
dict: annotation information consists of the following keys:
dict: Annotation information consists of the following keys:
- bboxes (np.ndarray): ground truth bboxes
- labels (np.ndarray): labels of ground truths
- bboxes (np.ndarray): Ground truth bboxes.
- labels (np.ndarray): Labels of ground truths.
"""
# Use index to get the annos, thus the evalhook could also use this api
info = self.data_infos[index]
......
mmdet3d/datasets/kitti_dataset.py
View file @ 21cb2aa6
......@@ -37,9 +37,9 @@ class KittiDataset(Custom3DDataset):
to its original format then converted them to `box_type_3d`.
Defaults to 'LiDAR' in this dataset. Available options includes
- 'LiDAR': box in LiDAR coordinates
- 'Depth': box in depth coordinates, usually for indoor dataset
- 'Camera': box in camera coordinates
- '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.
......@@ -88,13 +88,13 @@ class KittiDataset(Custom3DDataset):
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
- ann_info (dict): annotation info
- 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.
- ann_info (dict): Annotation info.
"""
info = self.data_infos[index]
sample_idx = info['image']['image_idx']
......@@ -131,11 +131,11 @@ class KittiDataset(Custom3DDataset):
dict: annotation information consists of the following keys:
- 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
- gt_labels (np.ndarray): labels of ground truths
- gt_names (list[str]): class names of ground truths
3D ground truth bboxes.
- gt_labels_3d (np.ndarray): Labels of ground truths.
- gt_bboxes (np.ndarray): 2D ground truth bboxes.
- gt_labels (np.ndarray): Labels of ground truths.
- gt_names (list[str]): Class names of ground truths.
"""
# Use index to get the annos, thus the evalhook could also use this api
info = self.data_infos[index]
......@@ -308,7 +308,7 @@ class KittiDataset(Custom3DDataset):
Default: None.
Returns:
dict[str, float]: results of each evaluation metric
dict[str, float]: Results of each evaluation metric.
"""
result_files, tmp_dir = self.format_results(results, pklfile_prefix)
from mmdet3d.core.evaluation import kitti_eval
......@@ -629,7 +629,7 @@ class KittiDataset(Custom3DDataset):
"""Results visualization.
Args:
results (list[dict]): list of bounding boxes results.
results (list[dict]): List of bounding boxes results.
out_dir (str): Output directory of visualization result.
"""
assert out_dir is not None, 'Expect out_dir, got none.'
......
mmdet3d/datasets/lyft_dataset.py
View file @ 21cb2aa6
......@@ -16,7 +16,7 @@ from .custom_3d import Custom3DDataset
@DATASETS.register_module()
class LyftDataset(Custom3DDataset):
"""Lyft Dataset.
r"""Lyft Dataset.
This class serves as the API for experiments on the Lyft Dataset.
......@@ -40,9 +40,9 @@ class LyftDataset(Custom3DDataset):
to its original format then converted them to `box_type_3d`.
Defaults to 'LiDAR' in this dataset. Available options includes
- 'LiDAR': box in LiDAR coordinates
- 'Depth': box in depth coordinates, usually for indoor dataset
- 'Camera': box in camera coordinates
- '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.
......@@ -185,12 +185,12 @@ class LyftDataset(Custom3DDataset):
index (int): Index of the annotation data to get.
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
- gt_labels_3d (np.ndarray): labels of ground truths
- gt_names (list[str]): class names of ground truths
3D ground truth bboxes.
- gt_labels_3d (np.ndarray): Labels of ground truths.
- gt_names (list[str]): Class names of ground truths.
"""
info = self.data_infos[index]
gt_bboxes_3d = info['gt_boxes']
......
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