Skip to content

GitLab

Commit 2eebdc2d authored by Yezhen Cong's avatar Yezhen Cong Committed by Tai-Wang
Browse files

[Refactor] Main code modification for coordinate system refactor (#677)

parent 26ab7ff2
Hide whitespace changes
Inline Side-by-side
Showing with 496 additions and 138 deletions
mmdet3d/core/bbox/structures/utils.py
View file @ 2eebdc2d
......@@ -3,84 +3,138 @@ import numpy as np
import torch
from logging import warning
from mmdet3d.core.utils import array_converter
@array_converter(apply_to=('val', ))
def limit_period(val, offset=0.5, period=np.pi):
"""Limit the value into a period for periodic function.
Args:
val (torch.Tensor): The value to be converted.
offset (float, optional): Offset to set the value range. \
val (torch.Tensor | np.ndarray): The value to be converted.
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 | np.ndarray): Value in the range of
[-offset * period, (1-offset) * period]
"""
return val - torch.floor(val / period + offset) * period
limited_val = val - torch.floor(val / period + offset) * period
return limited_val
def rotation_3d_in_axis(points, angles, axis=0):
@array_converter(apply_to=('points', 'angles'))
def rotation_3d_in_axis(points,
angles,
axis=0,
return_mat=False,
clockwise=False):
"""Rotate points by angles according to axis.
Args:
points (torch.Tensor): Points of shape (N, M, 3).
angles (torch.Tensor): Vector of angles in shape (N,)
points (np.ndarray | torch.Tensor | list | tuple ):
Points of shape (N, M, 3).
angles (np.ndarray | torch.Tensor | list | tuple | float):
Vector of angles in shape (N,)
axis (int, optional): The axis to be rotated. Defaults to 0.
return_mat: Whether or not return the rotation matrix (transposed).
Defaults to False.
clockwise: Whether the rotation is clockwise. Defaults to False.
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 | np.ndarray): Rotated points in shape (N, M, 3).
"""
batch_free = len(points.shape) == 2
if batch_free:
points = points[None]
if isinstance(angles, float) or len(angles.shape) == 0:
angles = torch.full(points.shape[:1], angles)
assert len(points.shape) == 3 and len(angles.shape) == 1 \
and points.shape[0] == angles.shape[0], f'Incorrect shape of points ' \
f'angles: {points.shape}, {angles.shape}'
assert points.shape[-1] in [2, 3], \
f'Points size should be 2 or 3 instead of {points.shape[-1]}'
rot_sin = torch.sin(angles)
rot_cos = torch.cos(angles)
ones = torch.ones_like(rot_cos)
zeros = torch.zeros_like(rot_cos)
if axis == 1:
rot_mat_T = torch.stack([
torch.stack([rot_cos, zeros, -rot_sin]),
torch.stack([zeros, ones, zeros]),
torch.stack([rot_sin, zeros, rot_cos])
])
elif axis == 2 or axis == -1:
rot_mat_T = torch.stack([
torch.stack([rot_cos, -rot_sin, zeros]),
torch.stack([rot_sin, rot_cos, zeros]),
torch.stack([zeros, zeros, ones])
])
elif axis == 0:
if points.shape[-1] == 3:
if axis == 1 or axis == -2:
rot_mat_T = torch.stack([
torch.stack([rot_cos, zeros, rot_sin]),
torch.stack([zeros, ones, zeros]),
torch.stack([-rot_sin, zeros, rot_cos])
])
elif axis == 2 or axis == -1:
rot_mat_T = torch.stack([
torch.stack([rot_cos, rot_sin, zeros]),
torch.stack([-rot_sin, rot_cos, zeros]),
torch.stack([zeros, zeros, ones])
])
elif axis == 0 or axis == -3:
rot_mat_T = torch.stack([
torch.stack([ones, zeros, zeros]),
torch.stack([zeros, rot_cos, rot_sin]),
torch.stack([zeros, -rot_sin, rot_cos])
])
else:
raise ValueError(f'axis should in range '
f'[-3, -2, -1, 0, 1, 2], got {axis}')
else:
rot_mat_T = torch.stack([
torch.stack([zeros, rot_cos, -rot_sin]),
torch.stack([zeros, rot_sin, rot_cos]),
torch.stack([ones, zeros, zeros])
torch.stack([rot_cos, rot_sin]),
torch.stack([-rot_sin, rot_cos])
])
if clockwise:
rot_mat_T = rot_mat_T.transpose(0, 1)
if points.shape[0] == 0:
points_new = points
else:
raise ValueError(f'axis should in range [0, 1, 2], got {axis}')
points_new = torch.einsum('aij,jka->aik', points, rot_mat_T)
if batch_free:
points_new = points_new.squeeze(0)
return torch.einsum('aij,jka->aik', (points, rot_mat_T))
if return_mat:
rot_mat_T = torch.einsum('jka->ajk', rot_mat_T)
if batch_free:
rot_mat_T = rot_mat_T.squeeze(0)
return points_new, rot_mat_T
else:
return points_new
@array_converter(apply_to=('boxes_xywhr', ))
def xywhr2xyxyr(boxes_xywhr):
"""Convert a rotated boxes in XYWHR format to XYXYR format.
Args:
boxes_xywhr (torch.Tensor): Rotated boxes in XYWHR format.
boxes_xywhr (torch.Tensor | np.ndarray): Rotated boxes in XYWHR format.
Returns:
torch.Tensor: Converted boxes in XYXYR format.
(torch.Tensor | np.ndarray): Converted boxes in XYXYR format.
"""
boxes = torch.zeros_like(boxes_xywhr)
half_w = boxes_xywhr[:, 2] / 2
half_h = boxes_xywhr[:, 3] / 2
boxes[:, 0] = boxes_xywhr[:, 0] - half_w
boxes[:, 1] = boxes_xywhr[:, 1] - half_h
boxes[:, 2] = boxes_xywhr[:, 0] + half_w
boxes[:, 3] = boxes_xywhr[:, 1] + half_h
boxes[:, 4] = boxes_xywhr[:, 4]
half_w = boxes_xywhr[..., 2] / 2
half_h = boxes_xywhr[..., 3] / 2
boxes[..., 0] = boxes_xywhr[..., 0] - half_w
boxes[..., 1] = boxes_xywhr[..., 1] - half_h
boxes[..., 2] = boxes_xywhr[..., 0] + half_w
boxes[..., 3] = boxes_xywhr[..., 1] + half_h
boxes[..., 4] = boxes_xywhr[..., 4]
return boxes
......@@ -91,6 +145,10 @@ def get_box_type(box_type):
box_type (str): The type of box structure.
The valid value are "LiDAR", "Camera", or "Depth".
Raises:
ValueError: A ValueError is raised when `box_type`
does not belong to the three valid types.
Returns:
tuple: Box type and box mode.
"""
......@@ -113,21 +171,24 @@ def get_box_type(box_type):
return box_type_3d, box_mode_3d
@array_converter(apply_to=('points_3d', 'proj_mat'))
def points_cam2img(points_3d, proj_mat, with_depth=False):
"""Project points from camera coordicates to image coordinates.
"""Project points in camera coordinates to image coordinates.
Args:
points_3d (torch.Tensor): Points in shape (N, 3).
proj_mat (torch.Tensor): Transformation matrix between coordinates.
points_3d (torch.Tensor | np.ndarray): Points in shape (N, 3)
proj_mat (torch.Tensor | np.ndarray):
Transformation matrix between coordinates.
with_depth (bool, optional): Whether to keep depth in the output.
Defaults to False.
Returns:
torch.Tensor: Points in image coordinates with shape [N, 2].
(torch.Tensor | np.ndarray): Points in image coordinates,
with shape [N, 2] if `with_depth=False`, else [N, 3].
"""
points_num = list(points_3d.shape)[:-1]
points_shape = list(points_3d.shape)
points_shape[-1] = 1
points_shape = np.concatenate([points_num, [1]], axis=0).tolist()
assert len(proj_mat.shape) == 2, 'The dimension of the projection'\
f' matrix should be 2 instead of {len(proj_mat.shape)}.'
d1, d2 = proj_mat.shape[:2]
......@@ -140,14 +201,15 @@ def points_cam2img(points_3d, proj_mat, with_depth=False):
proj_mat_expanded[:d1, :d2] = proj_mat
proj_mat = proj_mat_expanded
# previous implementation use new_zeros, new_one yeilds better results
points_4 = torch.cat(
[points_3d, points_3d.new_ones(*points_shape)], dim=-1)
point_2d = torch.matmul(points_4, proj_mat.t())
# previous implementation use new_zeros, new_one yields better results
points_4 = torch.cat([points_3d, points_3d.new_ones(points_shape)], dim=-1)
point_2d = points_4 @ proj_mat.T
point_2d_res = point_2d[..., :2] / point_2d[..., 2:3]
if with_depth:
return torch.cat([point_2d_res, point_2d[..., 2:3]], dim=-1)
point_2d_res = torch.cat([point_2d_res, point_2d[..., 2:3]], dim=-1)
return point_2d_res
......@@ -162,9 +224,9 @@ def mono_cam_box2vis(cam_box):
After applying this function, we can project and draw it on 2D images.
Args:
cam_box (:obj:`CameraInstance3DBoxes`): 3D bbox in camera coordinate \
system before conversion. Could be gt bbox loaded from dataset or \
network prediction output.
cam_box (:obj:`CameraInstance3DBoxes`): 3D bbox in camera coordinate
system before conversion. Could be gt bbox loaded from dataset
or network prediction output.
Returns:
:obj:`CameraInstance3DBoxes`: Box after conversion.
......
mmdet3d/core/bbox/transforms.py
View file @ 2eebdc2d
......@@ -32,7 +32,7 @@ def bbox3d2roi(bbox_list):
corresponding to a batch of images.
Returns:
torch.Tensor: Region of interests in shape (n, c), where \
torch.Tensor: Region of interests in shape (n, c), where
the channels are in order of [batch_ind, x, y ...].
"""
rois_list = []
......@@ -54,7 +54,7 @@ def bbox3d2result(bboxes, scores, labels, attrs=None):
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, ).
attrs (torch.Tensor, optional): Attributes with shape of (n, ). \
attrs (torch.Tensor, optional): Attributes with shape of (n, ).
Defaults to None.
Returns:
......
mmdet3d/core/points/base_points.py
View file @ 2eebdc2d
......@@ -4,6 +4,8 @@ import torch
import warnings
from abc import abstractmethod
from ..bbox.structures.utils import rotation_3d_in_axis
class BasePoints(object):
"""Base class for Points.
......@@ -141,7 +143,7 @@ class BasePoints(object):
"""Rotate points with the given rotation matrix or angle.
Args:
rotation (float, np.ndarray, torch.Tensor): Rotation matrix
rotation (float | np.ndarray | torch.Tensor): Rotation matrix
or angle.
axis (int): Axis to rotate at. Defaults to None.
"""
......@@ -154,28 +156,14 @@ class BasePoints(object):
axis = self.rotation_axis
if rotation.numel() == 1:
rot_sin = torch.sin(rotation)
rot_cos = torch.cos(rotation)
if axis == 1:
rot_mat_T = rotation.new_tensor([[rot_cos, 0, -rot_sin],
[0, 1, 0],
[rot_sin, 0, rot_cos]])
elif axis == 2 or axis == -1:
rot_mat_T = rotation.new_tensor([[rot_cos, -rot_sin, 0],
[rot_sin, rot_cos, 0],
[0, 0, 1]])
elif axis == 0:
rot_mat_T = rotation.new_tensor([[0, rot_cos, -rot_sin],
[0, rot_sin, rot_cos],
[1, 0, 0]])
else:
raise ValueError('axis should in range')
rot_mat_T = rot_mat_T.T
elif rotation.numel() == 9:
rot_mat_T = rotation
rotated_points, rot_mat_T = rotation_3d_in_axis(
self.tensor[:, :3][None], rotation, axis=axis, return_mat=True)
self.tensor[:, :3] = rotated_points.squeeze(0)
rot_mat_T = rot_mat_T.squeeze(0)
else:
raise NotImplementedError
self.tensor[:, :3] = self.tensor[:, :3] @ rot_mat_T
# rotation.numel() == 9
self.tensor[:, :3] = self.tensor[:, :3] @ rotation
rot_mat_T = rotation
return rot_mat_T
......
mmdet3d/core/utils/__init__.py
View file @ 2eebdc2d
# Copyright (c) OpenMMLab. All rights reserved.
from .array_converter import ArrayConverter, array_converter
from .gaussian import draw_heatmap_gaussian, gaussian_2d, gaussian_radius
__all__ = ['gaussian_2d', 'gaussian_radius', 'draw_heatmap_gaussian']
__all__ = [
'gaussian_2d', 'gaussian_radius', 'draw_heatmap_gaussian',
'ArrayConverter', 'array_converter'
]
mmdet3d/core/utils/array_converter.py 0 → 100644
View file @ 2eebdc2d
import functools
import numpy as np
import torch
from inspect import getfullargspec
def array_converter(to_torch=True,
apply_to=tuple(),
template_arg_name_=None,
recover=True):
"""Wrapper function for data-type agnostic processing.
First converts input arrays to PyTorch tensors or NumPy ndarrays
for middle calculation, then convert output to original data-type.
Args:
to_torch (Bool): Whether convert to PyTorch tensors
for middle calculation. Defaults to True.
apply_to (tuple[str]): The arguments to which we apply data-type
conversion. Defaults to an empty tuple.
template_arg_name_ (str): Argument serving as the template (
return arrays should have the same dtype and device
as the template). Defaults to None. If None, we will use the
first argument in `apply_to` as the template argument.
recover (Bool): Whether or not recover the wrapped function outputs
to the `template_arg_name_` type. Defaults to True.
Raises:
ValueError: When template_arg_name_ is not among all args, or
when apply_to contains an arg which is not among all args,
a ValueError will be raised. When the template argument or
an argument to convert is a list or tuple, and cannot be
converted to a NumPy array, a ValueError will be raised.
TypeError: When the type of the template argument or
an argument to convert does not belong to the above range,
or the contents of such an list-or-tuple-type argument
do not share the same data type, a TypeError is raised.
Returns:
(function): wrapped function.
Example:
>>> import torch
>>> import numpy as np
>>>
>>> # Use torch addition for a + b,
>>> # and convert return values to the type of a
>>> @array_converter(apply_to=('a', 'b'))
>>> def simple_add(a, b):
>>> return a + b
>>>
>>> a = np.array([1.1])
>>> b = np.array([2.2])
>>> simple_add(a, b)
>>>
>>> # Use numpy addition for a + b,
>>> # and convert return values to the type of b
>>> @array_converter(to_torch=False, apply_to=('a', 'b'),
>>> template_arg_name_='b')
>>> def simple_add(a, b):
>>> return a + b
>>>
>>> simple_add()
>>>
>>> # Use torch funcs for floor(a) if flag=True else ceil(a),
>>> # and return the torch tensor
>>> @array_converter(apply_to=('a',), recover=False)
>>> def floor_or_ceil(a, flag=True):
>>> return torch.floor(a) if flag else torch.ceil(a)
>>>
>>> floor_or_ceil(a, flag=False)
"""
def array_converter_wrapper(func):
"""Outer wrapper for the function."""
@functools.wraps(func)
def new_func(*args, **kwargs):
"""Inner wrapper for the arguments."""
if len(apply_to) == 0:
return func(*args, **kwargs)
func_name = func.__name__
arg_spec = getfullargspec(func)
arg_names = arg_spec.args
arg_num = len(arg_names)
default_arg_values = arg_spec.defaults
if default_arg_values is None:
default_arg_values = []
no_default_arg_num = len(arg_names) - len(default_arg_values)
kwonly_arg_names = arg_spec.kwonlyargs
kwonly_default_arg_values = arg_spec.kwonlydefaults
if kwonly_default_arg_values is None:
kwonly_default_arg_values = {}
all_arg_names = arg_names + kwonly_arg_names
# in case there are args in the form of *args
if len(args) > arg_num:
named_args = args[:arg_num]
nameless_args = args[arg_num:]
else:
named_args = args
nameless_args = []
# template argument data type is used for all array-like arguments
if template_arg_name_ is None:
template_arg_name = apply_to[0]
else:
template_arg_name = template_arg_name_
if template_arg_name not in all_arg_names:
raise ValueError(f'{template_arg_name} is not among the '
f'argument list of function {func_name}')
# inspect apply_to
for arg_to_apply in apply_to:
if arg_to_apply not in all_arg_names:
raise ValueError(f'{arg_to_apply} is not '
f'an argument of {func_name}')
new_args = []
new_kwargs = {}
converter = ArrayConverter()
target_type = torch.Tensor if to_torch else np.ndarray
# non-keyword arguments
for i, arg_value in enumerate(named_args):
if arg_names[i] in apply_to:
new_args.append(
converter.convert(
input_array=arg_value, target_type=target_type))
else:
new_args.append(arg_value)
if arg_names[i] == template_arg_name:
template_arg_value = arg_value
kwonly_default_arg_values.update(kwargs)
kwargs = kwonly_default_arg_values
# keyword arguments and non-keyword arguments using default value
for i in range(len(named_args), len(all_arg_names)):
arg_name = all_arg_names[i]
if arg_name in kwargs:
if arg_name in apply_to:
new_kwargs[arg_name] = converter.convert(
input_array=kwargs[arg_name],
target_type=target_type)
else:
new_kwargs[arg_name] = kwargs[arg_name]
else:
default_value = default_arg_values[i - no_default_arg_num]
if arg_name in apply_to:
new_kwargs[arg_name] = converter.convert(
input_array=default_value, target_type=target_type)
else:
new_kwargs[arg_name] = default_value
if arg_name == template_arg_name:
template_arg_value = kwargs[arg_name]
# add nameless args provided by *args (if exists)
new_args += nameless_args
return_values = func(*new_args, **new_kwargs)
converter.set_template(template_arg_value)
def recursive_recover(input_data):
if isinstance(input_data, (tuple, list)):
new_data = []
for item in input_data:
new_data.append(recursive_recover(item))
return tuple(new_data) if isinstance(input_data,
tuple) else new_data
elif isinstance(input_data, dict):
new_data = {}
for k, v in input_data.items():
new_data[k] = recursive_recover(v)
return new_data
elif isinstance(input_data, (torch.Tensor, np.ndarray)):
return converter.recover(input_data)
else:
return input_data
if recover:
return recursive_recover(return_values)
else:
return return_values
return new_func
return array_converter_wrapper
class ArrayConverter:
SUPPORTED_NON_ARRAY_TYPES = (int, float, np.int8, np.int16, np.int32,
np.int64, np.uint8, np.uint16, np.uint32,
np.uint64, np.float16, np.float32, np.float64)
def __init__(self, template_array=None):
if template_array is not None:
self.set_template(template_array)
def set_template(self, array):
"""Set template array.
Args:
array (tuple | list | int | float | np.ndarray | torch.Tensor):
Template array.
Raises:
ValueError: If input is list or tuple and cannot be converted to
to a NumPy array, a ValueError is raised.
TypeError: If input type does not belong to the above range,
or the contents of a list or tuple do not share the
same data type, a TypeError is raised.
"""
self.array_type = type(array)
self.is_num = False
self.device = 'cpu'
if isinstance(array, np.ndarray):
self.dtype = array.dtype
elif isinstance(array, torch.Tensor):
self.dtype = array.dtype
self.device = array.device
elif isinstance(array, (list, tuple)):
try:
array = np.array(array)
if array.dtype not in self.SUPPORTED_NON_ARRAY_TYPES:
raise TypeError
self.dtype = array.dtype
except (ValueError, TypeError):
print(f'The following list cannot be converted to'
f' a numpy array of supported dtype:\n{array}')
raise
elif isinstance(array, self.SUPPORTED_NON_ARRAY_TYPES):
self.array_type = np.ndarray
self.is_num = True
self.dtype = np.dtype(type(array))
else:
raise TypeError(f'Template type {self.array_type}'
f' is not supported.')
def convert(self, input_array, target_type=None, target_array=None):
"""Convert input array to target data type.
Args:
input_array (tuple | list | np.ndarray |
torch.Tensor | int | float ):
Input array. Defaults to None.
target_type (<class 'np.ndarray'> | <class 'torch.Tensor'>):
Type to which input array is converted. Defaults to None.
target_array (np.ndarray | torch.Tensor):
Template array to which input array is converted.
Defaults to None.
Raises:
ValueError: If input is list or tuple and cannot be converted to
to a NumPy array, a ValueError is raised.
TypeError: If input type does not belong to the above range,
or the contents of a list or tuple do not share the
same data type, a TypeError is raised.
"""
if isinstance(input_array, (list, tuple)):
try:
input_array = np.array(input_array)
if input_array.dtype not in self.SUPPORTED_NON_ARRAY_TYPES:
raise TypeError
except (ValueError, TypeError):
print(f'The input cannot be converted to'
f' a single-type numpy array:\n{input_array}')
raise
elif isinstance(input_array, self.SUPPORTED_NON_ARRAY_TYPES):
input_array = np.array(input_array)
array_type = type(input_array)
assert target_type is not None or target_array is not None, \
'must specify a target'
if target_type is not None:
assert target_type in (np.ndarray, torch.Tensor), \
'invalid target type'
if target_type == array_type:
return input_array
elif target_type == np.ndarray:
# default dtype is float32
converted_array = input_array.cpu().numpy().astype(np.float32)
else:
# default dtype is float32, device is 'cpu'
converted_array = torch.tensor(
input_array, dtype=torch.float32)
else:
assert isinstance(target_array, (np.ndarray, torch.Tensor)), \
'invalid target array type'
if isinstance(target_array, array_type):
return input_array
elif isinstance(target_array, np.ndarray):
converted_array = input_array.cpu().numpy().astype(
target_array.dtype)
else:
converted_array = target_array.new_tensor(input_array)
return converted_array
def recover(self, input_array):
assert isinstance(input_array, (np.ndarray, torch.Tensor)), \
'invalid input array type'
if isinstance(input_array, self.array_type):
return input_array
elif isinstance(input_array, torch.Tensor):
converted_array = input_array.cpu().numpy().astype(self.dtype)
else:
converted_array = torch.tensor(
input_array, dtype=self.dtype, device=self.device)
if self.is_num:
converted_array = converted_array.item()
return converted_array
mmdet3d/core/visualizer/show_result.py
View file @ 2eebdc2d
......@@ -111,16 +111,14 @@ def show_result(points,
if gt_bboxes is not None:
# bottom center to gravity center
gt_bboxes[..., 2] += gt_bboxes[..., 5] / 2
# the positive direction for yaw in meshlab is clockwise
gt_bboxes[:, 6] *= -1
_write_oriented_bbox(gt_bboxes,
osp.join(result_path, f'{filename}_gt.obj'))
if pred_bboxes is not None:
# bottom center to gravity center
pred_bboxes[..., 2] += pred_bboxes[..., 5] / 2
# the positive direction for yaw in meshlab is clockwise
pred_bboxes[:, 6] *= -1
_write_oriented_bbox(pred_bboxes,
osp.join(result_path, f'{filename}_pred.obj'))
......
mmdet3d/datasets/kitti_dataset.py
View file @ 2eebdc2d
......@@ -617,8 +617,6 @@ class KittiDataset(Custom3DDataset):
scores = box_dict['scores_3d']
labels = box_dict['labels_3d']
sample_idx = info['image']['image_idx']
# TODO: remove the hack of yaw
box_preds.tensor[:, -1] = box_preds.tensor[:, -1] - np.pi
box_preds.limit_yaw(offset=0.5, period=np.pi * 2)
if len(box_preds) == 0:
......
mmdet3d/datasets/lyft_dataset.py
View file @ 2eebdc2d
......@@ -517,16 +517,16 @@ def output_to_lyft_box(detection):
box_gravity_center = box3d.gravity_center.numpy()
box_dims = box3d.dims.numpy()
box_yaw = box3d.yaw.numpy()
# TODO: check whether this is necessary
# with dir_offset & dir_limit in the head
box_yaw = -box_yaw - np.pi / 2
# our LiDAR coordinate system -> Lyft box coordinate system
lyft_box_dims = box_dims[:, [1, 0, 2]]
box_list = []
for i in range(len(box3d)):
quat = Quaternion(axis=[0, 0, 1], radians=box_yaw[i])
box = LyftBox(
box_gravity_center[i],
box_dims[i],
lyft_box_dims[i],
quat,
label=labels[i],
score=scores[i])
......
mmdet3d/datasets/nuscenes_dataset.py
View file @ 2eebdc2d
......@@ -588,9 +588,9 @@ def output_to_nusc_box(detection):
box_gravity_center = box3d.gravity_center.numpy()
box_dims = box3d.dims.numpy()
box_yaw = box3d.yaw.numpy()
# TODO: check whether this is necessary
# with dir_offset & dir_limit in the head
box_yaw = -box_yaw - np.pi / 2
# our LiDAR coordinate system -> nuScenes box coordinate system
nus_box_dims = box_dims[:, [1, 0, 2]]
box_list = []
for i in range(len(box3d)):
......@@ -602,7 +602,7 @@ def output_to_nusc_box(detection):
# velo_val * np.cos(velo_ori), velo_val * np.sin(velo_ori), 0.0)
box = NuScenesBox(
box_gravity_center[i],
box_dims[i],
nus_box_dims[i],
quat,
label=labels[i],
score=scores[i],
......
mmdet3d/datasets/pipelines/data_augment_utils.py
View file @ 2eebdc2d
......@@ -21,8 +21,8 @@ def _rotation_box2d_jit_(corners, angle, rot_mat_T):
rot_sin = np.sin(angle)
rot_cos = np.cos(angle)
rot_mat_T[0, 0] = rot_cos
rot_mat_T[0, 1] = -rot_sin
rot_mat_T[1, 0] = rot_sin
rot_mat_T[0, 1] = rot_sin
rot_mat_T[1, 0] = -rot_sin
rot_mat_T[1, 1] = rot_cos
corners[:] = corners @ rot_mat_T
......@@ -211,8 +211,8 @@ def noise_per_box_v2_(boxes, valid_mask, loc_noises, rot_noises,
rot_sin = np.sin(current_box[0, -1])
rot_cos = np.cos(current_box[0, -1])
rot_mat_T[0, 0] = rot_cos
rot_mat_T[0, 1] = -rot_sin
rot_mat_T[1, 0] = rot_sin
rot_mat_T[0, 1] = rot_sin
rot_mat_T[1, 0] = -rot_sin
rot_mat_T[1, 1] = rot_cos
current_corners[:] = current_box[
0, 2:4] * corners_norm @ rot_mat_T + current_box[0, :2]
......@@ -264,18 +264,18 @@ def _rotation_matrix_3d_(rot_mat_T, angle, axis):
rot_mat_T[:] = np.eye(3)
if axis == 1:
rot_mat_T[0, 0] = rot_cos
rot_mat_T[0, 2] = -rot_sin
rot_mat_T[2, 0] = rot_sin
rot_mat_T[0, 2] = rot_sin
rot_mat_T[2, 0] = -rot_sin
rot_mat_T[2, 2] = rot_cos
elif axis == 2 or axis == -1:
rot_mat_T[0, 0] = rot_cos
rot_mat_T[0, 1] = -rot_sin
rot_mat_T[1, 0] = rot_sin
rot_mat_T[0, 1] = rot_sin
rot_mat_T[1, 0] = -rot_sin
rot_mat_T[1, 1] = rot_cos
elif axis == 0:
rot_mat_T[1, 1] = rot_cos
rot_mat_T[1, 2] = -rot_sin
rot_mat_T[2, 1] = rot_sin
rot_mat_T[1, 2] = rot_sin
rot_mat_T[2, 1] = -rot_sin
rot_mat_T[2, 2] = rot_cos
......
mmdet3d/datasets/pipelines/formating.py
View file @ 2eebdc2d
......@@ -137,7 +137,8 @@ class Collect3D(object):
'scale_factor', 'flip', 'pcd_horizontal_flip',
'pcd_vertical_flip', 'box_mode_3d', 'box_type_3d',
'img_norm_cfg', 'pcd_trans', 'sample_idx',
'pcd_scale_factor', 'pcd_rotation', 'pts_filename',
'pcd_scale_factor', 'pcd_rotation',
'pcd_rotation_angle', 'pts_filename',
'transformation_3d_flow')):
self.keys = keys
self.meta_keys = meta_keys
......
mmdet3d/datasets/pipelines/transforms_3d.py
View file @ 2eebdc2d
......@@ -394,7 +394,7 @@ class ObjectNoise(object):
gt_bboxes_3d = input_dict['gt_bboxes_3d']
points = input_dict['points']
# TODO: check this inplace function
# TODO: this is inplace operation
numpy_box = gt_bboxes_3d.tensor.numpy()
numpy_points = points.tensor.numpy()
......@@ -589,6 +589,7 @@ class GlobalRotScaleTrans(object):
if len(input_dict['bbox3d_fields']) == 0:
rot_mat_T = input_dict['points'].rotate(noise_rotation)
input_dict['pcd_rotation'] = rot_mat_T
input_dict['pcd_rotation_angle'] = noise_rotation
return
# rotate points with bboxes
......@@ -598,6 +599,7 @@ class GlobalRotScaleTrans(object):
noise_rotation, input_dict['points'])
input_dict['points'] = points
input_dict['pcd_rotation'] = rot_mat_T
input_dict['pcd_rotation_angle'] = noise_rotation
def _scale_bbox_points(self, input_dict):
"""Private function to scale bounding boxes and points.
......
mmdet3d/datasets/waymo_dataset.py
View file @ 2eebdc2d
......@@ -494,7 +494,6 @@ class WaymoDataset(KittiDataset):
scores = box_dict['scores_3d']
labels = box_dict['labels_3d']
sample_idx = info['image']['image_idx']
# TODO: remove the hack of yaw
box_preds.limit_yaw(offset=0.5, period=np.pi * 2)
if len(box_preds) == 0:
......
mmdet3d/models/dense_heads/anchor3d_head.py
View file @ 2eebdc2d
......@@ -51,15 +51,15 @@ class Anchor3DHead(BaseModule, AnchorTrainMixin):
type='Anchor3DRangeGenerator',
range=[0, -39.68, -1.78, 69.12, 39.68, -1.78],
strides=[2],
sizes=[[1.6, 3.9, 1.56]],
sizes=[[3.9, 1.6, 1.56]],
rotations=[0, 1.57],
custom_values=[],
reshape_out=False),
assigner_per_size=False,
assign_per_class=False,
diff_rad_by_sin=True,
dir_offset=0,
dir_limit_offset=1,
dir_offset=-np.pi / 2,
dir_limit_offset=0,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
loss_cls=dict(
type='CrossEntropyLoss',
......
mmdet3d/models/dense_heads/anchor_free_mono3d_head.py
View file @ 2eebdc2d
......@@ -79,6 +79,7 @@ class AnchorFreeMono3DHead(BaseMono3DDenseHead):
use_direction_classifier=True,
diff_rad_by_sin=True,
dir_offset=0,
dir_limit_offset=0,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
......
mmdet3d/models/dense_heads/fcos_mono3d_head.py
View file @ 2eebdc2d
......@@ -217,6 +217,7 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
@staticmethod
def get_direction_target(reg_targets,
dir_offset=0,
dir_limit_offset=0,
num_bins=2,
one_hot=True):
"""Encode direction to 0 ~ num_bins-1.
......@@ -231,7 +232,8 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
torch.Tensor: Encoded direction targets.
"""
rot_gt = reg_targets[..., 6]
offset_rot = limit_period(rot_gt - dir_offset, 0, 2 * np.pi)
offset_rot = limit_period(rot_gt - dir_offset, dir_limit_offset,
2 * np.pi)
dir_cls_targets = torch.floor(offset_rot /
(2 * np.pi / num_bins)).long()
dir_cls_targets = torch.clamp(dir_cls_targets, min=0, max=num_bins - 1)
......@@ -377,7 +379,10 @@ class FCOSMono3DHead(AnchorFreeMono3DHead):
if self.use_direction_classifier:
pos_dir_cls_targets = self.get_direction_target(
pos_bbox_targets_3d, self.dir_offset, one_hot=False)
pos_bbox_targets_3d,
self.dir_offset,
self.dir_limit_offset,
one_hot=False)
if self.diff_rad_by_sin:
pos_bbox_preds, pos_bbox_targets_3d = self.add_sin_difference(
......
mmdet3d/models/dense_heads/free_anchor3d_head.py
View file @ 2eebdc2d
......@@ -195,6 +195,7 @@ class FreeAnchor3DHead(Anchor3DHead):
matched_anchors,
matched_object_targets,
self.dir_offset,
self.dir_limit_offset,
one_hot=False)
loss_dir = self.loss_dir(
dir_cls_preds_[matched].transpose(-2, -1),
......
mmdet3d/models/dense_heads/groupfree3d_head.py
View file @ 2eebdc2d
......@@ -951,7 +951,7 @@ class GroupFree3DHead(BaseModule):
box_dim=bbox.shape[-1],
with_yaw=self.bbox_coder.with_rot,
origin=(0.5, 0.5, 0.5))
box_indices = bbox.points_in_boxes(points)
box_indices = bbox.points_in_boxes_batch(points)
corner3d = bbox.corners
minmax_box3d = corner3d.new(torch.Size((corner3d.shape[0], 6)))
......
mmdet3d/models/dense_heads/parta2_rpn_head.py
View file @ 2eebdc2d
......@@ -60,15 +60,15 @@ class PartA2RPNHead(Anchor3DHead):
type='Anchor3DRangeGenerator',
range=[0, -39.68, -1.78, 69.12, 39.68, -1.78],
strides=[2],
sizes=[[1.6, 3.9, 1.56]],
sizes=[[3.9, 1.6, 1.56]],
rotations=[0, 1.57],
custom_values=[],
reshape_out=False),
assigner_per_size=False,
assign_per_class=False,
diff_rad_by_sin=True,
dir_offset=0,
dir_limit_offset=1,
dir_offset=-np.pi / 2,
dir_limit_offset=0,
bbox_coder=dict(type='DeltaXYZWLHRBBoxCoder'),
loss_cls=dict(
type='CrossEntropyLoss',
......
mmdet3d/models/dense_heads/ssd_3d_head.py
View file @ 2eebdc2d
......@@ -464,9 +464,7 @@ class SSD3DHead(VoteHead):
bbox_selected, score_selected, labels = self.multiclass_nms_single(
obj_scores[b], sem_scores[b], bbox3d[b], points[b, ..., :3],
input_metas[b])
# fix the wrong direction
# To do: remove this ops
bbox_selected[..., 6] += np.pi
bbox = input_metas[b]['box_type_3d'](
bbox_selected.clone(),
box_dim=bbox_selected.shape[-1],
......@@ -489,23 +487,14 @@ class SSD3DHead(VoteHead):
Returns:
tuple[torch.Tensor]: Bounding boxes, scores and labels.
"""
num_bbox = bbox.shape[0]
bbox = input_meta['box_type_3d'](
bbox.clone(),
box_dim=bbox.shape[-1],
with_yaw=self.bbox_coder.with_rot,
origin=(0.5, 0.5, 0.5))
if isinstance(bbox, LiDARInstance3DBoxes):
box_idx = bbox.points_in_boxes(points)
box_indices = box_idx.new_zeros([num_bbox + 1])
box_idx[box_idx == -1] = num_bbox
box_indices.scatter_add_(0, box_idx.long(),
box_idx.new_ones(box_idx.shape))
box_indices = box_indices[:-1]
nonempty_box_mask = box_indices >= 0
elif isinstance(bbox, DepthInstance3DBoxes):
box_indices = bbox.points_in_boxes(points)
if isinstance(bbox, (LiDARInstance3DBoxes, DepthInstance3DBoxes)):
box_indices = bbox.points_in_boxes_batch(points)
nonempty_box_mask = box_indices.T.sum(1) >= 0
else:
raise NotImplementedError('Unsupported bbox type!')
......@@ -560,18 +549,8 @@ class SSD3DHead(VoteHead):
tuple[torch.Tensor]: Flags indicating whether each point is
inside bbox and the index of box where each point are in.
"""
# TODO: align points_in_boxes function in each box_structures
num_bbox = bboxes_3d.tensor.shape[0]
if isinstance(bboxes_3d, LiDARInstance3DBoxes):
assignment = bboxes_3d.points_in_boxes(points).long()
points_mask = assignment.new_zeros(
[assignment.shape[0], num_bbox + 1])
assignment[assignment == -1] = num_bbox
points_mask.scatter_(1, assignment.unsqueeze(1), 1)
points_mask = points_mask[:, :-1]
assignment[assignment == num_bbox] = num_bbox - 1
elif isinstance(bboxes_3d, DepthInstance3DBoxes):
points_mask = bboxes_3d.points_in_boxes(points)
if isinstance(bboxes_3d, (LiDARInstance3DBoxes, DepthInstance3DBoxes)):
points_mask = bboxes_3d.points_in_boxes_batch(points)
assignment = points_mask.argmax(dim=-1)
else:
raise NotImplementedError('Unsupported bbox type!')
......
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