downstream/semseg/lib/voxelizer.py [14:95]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def M(axis, theta): return expm(np.cross(np.eye(3), axis / norm(axis) * theta)) class Voxelizer: def __init__(self, voxel_size=1, clip_bound=None, use_augmentation=False, scale_augmentation_bound=None, rotation_augmentation_bound=None, translation_augmentation_ratio_bound=None, ignore_label=255): """ Args: voxel_size: side length of a voxel clip_bound: boundary of the voxelizer. Points outside the bound will be deleted expects either None or an array like ((-100, 100), (-100, 100), (-100, 100)). scale_augmentation_bound: None or (0.9, 1.1) rotation_augmentation_bound: None or ((np.pi / 6, np.pi / 6), None, None) for 3 axis. Use random order of x, y, z to prevent bias. translation_augmentation_bound: ((-5, 5), (0, 0), (-10, 10)) ignore_label: label assigned for ignore (not a training label). """ self.voxel_size = voxel_size self.clip_bound = clip_bound self.ignore_label = ignore_label # Augmentation self.use_augmentation = use_augmentation self.scale_augmentation_bound = scale_augmentation_bound self.rotation_augmentation_bound = rotation_augmentation_bound self.translation_augmentation_ratio_bound = translation_augmentation_ratio_bound def get_transformation_matrix(self): voxelization_matrix, rotation_matrix = np.eye(4), np.eye(4) # Get clip boundary from config or pointcloud. # Get inner clip bound to crop from. # Transform pointcloud coordinate to voxel coordinate. # 1. Random rotation rot_mat = np.eye(3) if self.use_augmentation and self.rotation_augmentation_bound is not None: if isinstance(self.rotation_augmentation_bound, collections.Iterable): rot_mats = [] for axis_ind, rot_bound in enumerate(self.rotation_augmentation_bound): theta = 0 axis = np.zeros(3) axis[axis_ind] = 1 if rot_bound is not None: theta = np.random.uniform(*rot_bound) rot_mats.append(M(axis, theta)) # Use random order np.random.shuffle(rot_mats) rot_mat = rot_mats[0] @ rot_mats[1] @ rot_mats[2] else: raise ValueError() rotation_matrix[:3, :3] = rot_mat # 2. Scale and translate to the voxel space. scale = 1 / self.voxel_size if self.use_augmentation and self.scale_augmentation_bound is not None: scale *= np.random.uniform(*self.scale_augmentation_bound) np.fill_diagonal(voxelization_matrix[:3, :3], scale) # Get final transformation matrix. return voxelization_matrix, rotation_matrix def clip(self, coords, center=None, trans_aug_ratio=None): bound_min = np.min(coords, 0).astype(float) bound_max = np.max(coords, 0).astype(float) bound_size = bound_max - bound_min if center is None: center = bound_min + bound_size * 0.5 if trans_aug_ratio is not None: trans = np.multiply(trans_aug_ratio, bound_size) center += trans lim = self.clip_bound if isinstance(self.clip_bound, (int, float)): if bound_size.max() < self.clip_bound: return None else: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - downstream/votenet_det_new/models/backbone/sparseconv/voxelizer.py [14:95]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def M(axis, theta): return expm(np.cross(np.eye(3), axis / norm(axis) * theta)) class Voxelizer: def __init__(self, voxel_size=1, clip_bound=None, use_augmentation=False, scale_augmentation_bound=None, rotation_augmentation_bound=None, translation_augmentation_ratio_bound=None, ignore_label=255): """ Args: voxel_size: side length of a voxel clip_bound: boundary of the voxelizer. Points outside the bound will be deleted expects either None or an array like ((-100, 100), (-100, 100), (-100, 100)). scale_augmentation_bound: None or (0.9, 1.1) rotation_augmentation_bound: None or ((np.pi / 6, np.pi / 6), None, None) for 3 axis. Use random order of x, y, z to prevent bias. translation_augmentation_bound: ((-5, 5), (0, 0), (-10, 10)) ignore_label: label assigned for ignore (not a training label). """ self.voxel_size = voxel_size self.clip_bound = clip_bound self.ignore_label = ignore_label # Augmentation self.use_augmentation = use_augmentation self.scale_augmentation_bound = scale_augmentation_bound self.rotation_augmentation_bound = rotation_augmentation_bound self.translation_augmentation_ratio_bound = translation_augmentation_ratio_bound def get_transformation_matrix(self): voxelization_matrix, rotation_matrix = np.eye(4), np.eye(4) # Get clip boundary from config or pointcloud. # Get inner clip bound to crop from. # Transform pointcloud coordinate to voxel coordinate. # 1. Random rotation rot_mat = np.eye(3) if self.use_augmentation and self.rotation_augmentation_bound is not None: if isinstance(self.rotation_augmentation_bound, collections.Iterable): rot_mats = [] for axis_ind, rot_bound in enumerate(self.rotation_augmentation_bound): theta = 0 axis = np.zeros(3) axis[axis_ind] = 1 if rot_bound is not None: theta = np.random.uniform(*rot_bound) rot_mats.append(M(axis, theta)) # Use random order np.random.shuffle(rot_mats) rot_mat = rot_mats[0] @ rot_mats[1] @ rot_mats[2] else: raise ValueError() rotation_matrix[:3, :3] = rot_mat # 2. Scale and translate to the voxel space. scale = 1 / self.voxel_size if self.use_augmentation and self.scale_augmentation_bound is not None: scale *= np.random.uniform(*self.scale_augmentation_bound) np.fill_diagonal(voxelization_matrix[:3, :3], scale) # Get final transformation matrix. return voxelization_matrix, rotation_matrix def clip(self, coords, center=None, trans_aug_ratio=None): bound_min = np.min(coords, 0).astype(float) bound_max = np.max(coords, 0).astype(float) bound_size = bound_max - bound_min if center is None: center = bound_min + bound_size * 0.5 if trans_aug_ratio is not None: trans = np.multiply(trans_aug_ratio, bound_size) center += trans lim = self.clip_bound if isinstance(self.clip_bound, (int, float)): if bound_size.max() < self.clip_bound: return None else: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -