def __init__(self, vsize_xyz, coors_range_xyz, num_point_features, max_num_points_per_voxel, max_num_voxels):
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
self.spconv_ver = 1
except:
try:
from spconv.utils import VoxelGenerator
self.spconv_ver = 1
except:
from spconv.utils import Point2VoxelCPU3d as VoxelGenerator
self.spconv_ver = 2
if self.spconv_ver == 1:
self._voxel_generator = VoxelGenerator(
voxel_size=vsize_xyz,
point_cloud_range=coors_range_xyz,
max_num_points=max_num_points_per_voxel,
max_voxels=max_num_voxels
)
else:
self._voxel_generator = VoxelGenerator(
vsize_xyz=vsize_xyz,
coors_range_xyz=coors_range_xyz,
num_point_features=num_point_features,
max_num_points_per_voxel=max_num_points_per_voxel,
max_num_voxels=max_num_voxels
)
def dataset_init(self, class_names, logger):
self.db_sampler = None
db_sampler_cfg = cfg.DATA_CONFIG.AUGMENTATION.DB_SAMPLER
if self.training and db_sampler_cfg.ENABLED:
db_infos = []
for db_info_path in db_sampler_cfg.DB_INFO_PATH:
db_info_path = cfg.ROOT_DIR / db_info_path
with open(str(db_info_path), 'rb') as f:
infos = pickle.load(f)
if db_infos.__len__() == 0:
db_infos = infos
else:
[
db_infos[cls].extend(infos[cls])
for cls in db_infos.keys()
]
self.db_sampler = DataBaseSampler(db_infos=db_infos,
sampler_cfg=db_sampler_cfg,
class_names=class_names,
logger=logger)
voxel_generator_cfg = cfg.DATA_CONFIG.VOXEL_GENERATOR
self.voxel_generator = VoxelGenerator(
voxel_size=voxel_generator_cfg.VOXEL_SIZE,
point_cloud_range=cfg.DATA_CONFIG.POINT_CLOUD_RANGE,
max_num_points=voxel_generator_cfg.MAX_POINTS_PER_VOXEL)
def transform_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None):
if data_dict is None:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
return partial(self.transform_points_to_voxels,
voxel_generator=voxel_generator)
points = data_dict['points']
voxels, coordinates, num_points = voxel_generator.generate(points)
if not data_dict['use_lead_xyz']:
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict
def transform_augmented_lidar_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None):
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
self.voxel_augmented_lidar_labels = config.VOXEL_AUGMENTED_LIDAR_LABELS
return partial(self.transform_augmented_lidar_points_to_voxels,
voxel_generator=voxel_generator)
points = data_dict['points']
voxel_output = voxel_generator.generate(points)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
assert data_dict[
'use_lead_xyz'], 'use_lead_xyz is set False! xyz should be used for voxelization!'
if self.mode == 'train':
voxel_labels = voxels[
...,
3:] #[M, max_points, ndim] float tensor. only contain points
assert voxel_labels.shape[-1] == len(self.voxel_augmented_lidar_labels), \
'voxel_labels.shape[-1]='+str(voxel_labels.shape[-1])+' len(self.voxel_augmented_lidar_labels)='+str(len(self.voxel_augmented_lidar_labels))
for idx, x in enumerate(self.voxel_augmented_lidar_labels):
if x == 'drivable_area_bool':
data_dict['voxels_drivable_cls_labels'] = np.max(
voxel_labels[:, :, idx],
axis=1).reshape(-1, 1) #binary 1 or 0
elif x == 'lidar_ground_bool':
data_dict['voxels_ground_cls_labels'] = np.max(
voxel_labels[:, :, idx],
axis=1).reshape(-1, 1) #binary 1 or 0
elif x == 'ground_height':
data_dict['voxels_ground_reg_labels'] = np.min(
voxel_labels[:, :, idx], axis=1).reshape(-1, 1) #float
voxels = voxels[..., :3] # use xyz as voxel data
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict
def dataset_init(self, class_names, logger):
self.db_sampler = None
db_sampler_cfg = cfg.DATA_CONFIG.AUGMENTATION.DB_SAMPLER
if self.training and db_sampler_cfg.ENABLED:
db_infos = []
for db_info_path in db_sampler_cfg.DB_INFO_PATH:
db_info_path = cfg.ROOT_DIR / db_info_path
with open(str(db_info_path), 'rb') as f:
infos = pickle.load(f)
if db_infos.__len__() == 0:
db_infos = infos
else:
[db_infos[cls].extend(infos[cls]) for cls in db_infos.keys()]
self.db_sampler = DataBaseSampler(
db_infos=db_infos, sampler_cfg=db_sampler_cfg, class_names=class_names, logger=logger
)
voxel_generator_cfg = cfg.DATA_CONFIG.VOXEL_GENERATOR
self.voxel_generator = VoxelGenerator(
voxel_size=voxel_generator_cfg.VOXEL_SIZE,
point_cloud_range=cfg.DATA_CONFIG.POINT_CLOUD_RANGE,
max_num_points=voxel_generator_cfg.MAX_POINTS_PER_VOXEL
)
if cfg.MODEL.NAME == 'MVF':
self.mvf_feature = PointCloudVoxel(0,
voxel_generator_cfg.BEV_FEATURE_SIZE_XY[0], voxel_generator_cfg.BEV_FEATURE_SIZE_XY[1], 1,
voxel_generator_cfg.BEV_RANGE[0], voxel_generator_cfg.BEV_RANGE[1], voxel_generator_cfg.BEV_RANGE[2], voxel_generator_cfg.BEV_RANGE[3], voxel_generator_cfg.BEV_RANGE[4], voxel_generator_cfg.BEV_RANGE[5],
0,
voxel_generator_cfg.FV_FEATURE_SIZE_ROW_COL[0], voxel_generator_cfg.FV_FEATURE_SIZE_ROW_COL[1],
voxel_generator_cfg.FV_RANGE_THETA_PHI[0], voxel_generator_cfg.FV_RANGE_THETA_PHI[1], voxel_generator_cfg.FV_RANGE_THETA_PHI[2], voxel_generator_cfg.FV_RANGE_THETA_PHI[3])
def sponv_process_pointcloud(point_cloud, template=False, is_testset=False):
if not is_testset:
point_cloud = shuffle_points(point_cloud)
max_number_of_voxel = 16000
else:
max_number_of_voxel = 40000
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
if template:
point_cloud_range = [cfg.TEMPLATE_X_MIN, cfg.TEMPLATE_Y_MIN, cfg.TEMPLATE_Z_MIN, cfg.TEMPLATE_X_MAX, cfg.TEMPLATE_Y_MAX, cfg.TEMPLATE_Z_MAX]
else:
point_cloud_range = [cfg.SCENE_X_MIN, cfg.SCENE_Y_MIN, cfg.SCENE_Z_MIN, cfg.SCENE_X_MAX, cfg.SCENE_Y_MAX, cfg.SCENE_Z_MAX]
voxel_size = np.array([cfg.VOXEL_X_SIZE, cfg.VOXEL_Y_SIZE, cfg.VOXEL_Z_SIZE], dtype = np.float32)
max_point_number = cfg.VOXEL_POINT_COUNT
voxel_generator = VoxelGenerator(
voxel_size=voxel_size,
point_cloud_range=point_cloud_range,
max_num_points=max_point_number,
max_voxels=max_number_of_voxel
)
voxel_output = voxel_generator.generate(point_cloud)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
voxel_dict = {'feature_buffer': voxels,
'coordinate_buffer': coordinates,
'number_buffer': num_points}
return voxel_dict
def initialize_model(args):
global model, voxel_generator
cfg = Config.fromfile(args.config)
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
if args.checkpoint is not None:
load_checkpoint(model, args.checkpoint, map_location="cpu")
# print(model)
if args.fp16:
print("cast model to fp16")
model = model.half()
model = model.cuda()
model.eval()
global device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
range = cfg.voxel_generator.range
voxel_size = cfg.voxel_generator.voxel_size
max_points_in_voxel = cfg.voxel_generator.max_points_in_voxel
max_voxel_num = cfg.voxel_generator.max_voxel_num[1]
voxel_generator = VoxelGenerator(voxel_size=voxel_size,
point_cloud_range=range,
max_num_points=max_points_in_voxel,
max_voxels=max_voxel_num)
return model
def transform_points_to_voxels(self, data_dict=None, config=None, voxel_generator=None):
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode]
)
grid_size = (self.point_cloud_range[3:6] - self.point_cloud_range[0:3]) / np.array(config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
return partial(self.transform_points_to_voxels, voxel_generator=voxel_generator)
points = data_dict['points']
color = get_color(data_dict)
points = np.concatenate([points, color], axis=1)
voxel_output = voxel_generator.generate(points)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
if not data_dict['use_lead_xyz']:
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict
def transform_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None):
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
self.max_voxels = config.MAX_NUMBER_OF_VOXELS[self.mode]
self.skip_voxel_generator = config.get('SKIP_VOXEL_GENERATOR',
False)
return partial(self.transform_points_to_voxels,
voxel_generator=voxel_generator)
if self.skip_voxel_generator:
points = data_dict['points']
pc_range_min = np.array(self.point_cloud_range[:3]).reshape(-1, 3)
voxel_size_array = np.array(self.voxel_size).reshape(-1, 3)
keep = common_utils.mask_points_by_range_hard(
points, self.point_cloud_range)
chosen_points = points[keep]
chosen_points = chosen_points[:self.max_voxels, :]
coords = (chosen_points[:, :3] - pc_range_min) // voxel_size_array
coords = coords.astype(int)
num_points = np.ones(chosen_points.shape[0])
data_dict['voxels'] = chosen_points
data_dict['voxel_coords'] = coords[:, [2, 1, 0]]
data_dict['voxel_num_points'] = num_points
else:
points = data_dict['points']
voxel_output = voxel_generator.generate(points)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
if not data_dict['use_lead_xyz']:
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict
def transform_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None):
# 在类初始化时调用
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
return partial(self.transform_points_to_voxels,
voxel_generator=voxel_generator)
points = data_dict['points']
# res = {
# "voxels": voxels,
# "coordinates": coors,
# "num_points_per_voxel": num_points_per_voxel,
# "voxel_point_mask": voxel_point_mask,
# "voxel_num": voxel_num
# "voxel_point_mask": res["voxel_point_mask"].reshape(
# -1, max_points, 1)
# }
voxel_output = voxel_generator.generate(points)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
if not data_dict['use_lead_xyz']: # True
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict
def transform_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None):
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
return partial(self.transform_points_to_voxels,
voxel_generator=voxel_generator)
points = data_dict['points']
voxel_output = voxel_generator.generate(points)
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
if not data_dict['use_lead_xyz']:
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
voxel_features, voxel_num_points = data_dict['voxels'], data_dict[
'voxel_num_points']
points_mean = np.sum(voxel_features[:, :, :], axis=1, keepdims=False)
num_points = num_points.astype(voxels.dtype).reshape((-1, 1))
normalizer = np.clip(num_points, a_min=1.0, a_max=6.0)
points_mean = points_mean / normalizer
data_dict['voxel_features'] = points_mean
return data_dict
def transform_points_to_rangevoxels(self,
data_dict=None,
config=None,
voxel_generator=None):
if data_dict is None:
from sphconv import VoxelGenerator
voxel_generator = VoxelGenerator(config.v_res, config.h_res,
config.d_res, config.v_range,
config.h_range, config.d_range,
config.log)
self.grid_size = np.array(
[config.d_res, config.h_res, config.v_res]).astype(np.int64)
return partial(self.transform_points_to_rangevoxels,
voxel_generator=voxel_generator)
points = data_dict['points']
rangeV = voxel_generator.generate(points)
data_dict['rangeV'] = rangeV
return data_dict
def build(voxel_config):
"""Builds a tensor dictionary based on the InputReader config.
Args:
input_reader_config: A input_reader_pb2.InputReader object.
Returns:
A tensor dict based on the input_reader_config.
Raises:
ValueError: On invalid input reader proto.
ValueError: If no input paths are specified.
"""
if not isinstance(voxel_config, (voxel_generator_pb2.VoxelGenerator)):
raise ValueError('input_reader_config not of type '
'input_reader_pb2.InputReader.')
voxel_generator = VoxelGenerator(
voxel_size=list(voxel_config.voxel_size),
point_cloud_range=list(voxel_config.point_cloud_range),
max_num_points=voxel_config.max_number_of_points_per_voxel,
max_voxels=20000)
return voxel_generator
def noise_robustness(batch_size, ret):
"""
Add noise points around every ground truth box for SECOND and Point-RCNN.
The idea is proposed in TANet (AAAI 2020), https://arxiv.org/pdf/1912.05163.pdf.
How to use:
For now, this function should be added to line 179 of pcdet/datasets/dataset.py
TODO: Integrate with pcdet/datasets/dataset.py
Change no_of_pts to number of uniformly generated noise points desired
around each GT bounding box.
:param batch_size:
:param ret:
:return:
"""
if True:
np.random.seed(0) # Numpy module.
voxels_flag = True
no_of_pts = 100
voxel_list = []
coords_list = []
num_points_list = []
for k in range(batch_size):
for i_box in range(len(ret['gt_boxes'][k])):
bbox = ret['gt_boxes'][k][i_box]
cx = bbox[0]
cy = bbox[1]
cz = bbox[2]
l = bbox[3]
w = bbox[4]
h = bbox[5]
z1 = np.random.uniform(cx + l // 2, cx + 3 * l,
(no_of_pts // 2, 1))
z2 = np.random.uniform(cx - l // 2, cx - 3 * l,
(no_of_pts // 2, 1))
z = np.concatenate([z1, z2], 0)
y1 = np.random.uniform(cy + w // 2, cy + 3 * w,
(no_of_pts // 2, 1))
y2 = np.random.uniform(cy - w // 2, cy - 3 * w,
(no_of_pts // 2, 1))
y = np.concatenate([y1, y2], 0)
x1 = np.random.uniform(cz + h // 2, cz + 3 * h,
(no_of_pts // 2, 1))
x2 = np.random.uniform(cz - h // 2, cz - 3 * h,
(no_of_pts // 2, 1))
x = np.concatenate([x1, x2], 0)
r = np.ones([no_of_pts, 1])
b = np.zeros([no_of_pts, 1]) + k
noise = np.concatenate([b, z, y, x, r], 1)
ret['points'] = np.concatenate([ret['points'], noise], 0)
if voxels_flag:
voxel_generator = VoxelGenerator(
voxel_size=[0.05, 0.05, 0.1],
point_cloud_range=[0, -40, -3, 70.4, 40, 1],
max_num_points=5,
max_voxels=40000,
)
batch_mask = ret['points'][:, 0] == k
points_extract = ret['points'][batch_mask, :]
voxels, coordinates, num_points = voxel_generator.generate(
points_extract[:, 1:])
voxel_list.append(voxels)
coords_list.append(coordinates)
num_points_list.append(num_points)
if voxels_flag:
ret['voxels'] = np.concatenate(voxel_list, axis=0)
ret['voxel_num_points'] = np.concatenate(num_points_list, axis=0)
coors = []
for i, coor in enumerate(coords_list):
coor_pad = np.pad(coor, ((0, 0), (1, 0)),
mode='constant',
constant_values=i)
coors.append(coor_pad)
ret['voxel_coords'] = np.concatenate(coors, axis=0)
return ret
def __init__(self, cfg):
self.split = "train" ### Default is training
self.label_objs = []
self.data_paths = []
self.label_paths = []
self.cfg = cfg
self.batchsize_per_replica = cfg["BATCHSIZE_PER_REPLICA"]
self.label_sources = [] #cfg["LABEL_SOURCES"]
self.dataset_names = cfg["DATASET_NAMES"]
self.label_type = cfg["LABEL_TYPE"]
self.AUGMENT_COORDS_TO_FEATS = False #optional
self._labels_init = False
self._get_data_files("train")
self.data_objs = np.load(
self.data_paths[0]) ### Only load the first one for now
#### Add the voxelizer here
if ("Lidar" in cfg) and cfg["VOX"]:
self.VOXEL_SIZE = [0.1, 0.1, 0.2]
self.point_cloud_range = POINT_RANGE #np.array([ 0. , -75. , -3. , 75.0, 75. , 3. ], dtype=np.float32)
self.MAX_POINTS_PER_VOXEL = 5
self.MAX_NUMBER_OF_VOXELS = 16000
self.voxel_generator = VoxelGenerator(
voxel_size=self.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=self.MAX_POINTS_PER_VOXEL,
max_voxels=self.MAX_NUMBER_OF_VOXELS)
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
self.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = self.VOXEL_SIZE
elif cfg["VOX"]:
augment_data = (self.split == "TRAIN")
#### Vox parameters here
self.VOXEL_SIZE = 0.05 #0.02 # 5cm
self.CLIP_BOUND = None #(-1000, -1000, -1000, 1000, 1000, 1000)
self.data_aug_color_trans_ratio = 0.1
self.data_aug_color_jitter_std = 0.05
self.ELASTIC_DISTORT_PARAMS = ((0.2, 0.4), (0.8, 1.6))
if augment_data:
self.prevoxel_transform_train = []
self.prevoxel_transform_train.append(
transforms.ElasticDistortion(self.ELASTIC_DISTORT_PARAMS))
self.prevoxel_transform = transforms.Compose(
self.prevoxel_transform_train)
self.input_transforms = []
self.input_transforms += [
transforms.RandomDropout(0.2),
transforms.RandomHorizontalFlip('z', False),
#transforms.ChromaticAutoContrast(),
transforms.ChromaticTranslation(
self.data_aug_color_trans_ratio),
transforms.ChromaticJitter(self.data_aug_color_jitter_std),
# t.HueSaturationTranslation(config.data_aug_hue_max, config.data_aug_saturation_max),
]
self.input_transforms = transforms.Compose(
self.input_transforms)
# Coordinate Augmentation Arguments: Unlike feature augmentation, coordinate
# augmentation has to be done before voxelization
self.SCALE_AUGMENTATION_BOUND = (0.9, 1.1)
self.ROTATION_AUGMENTATION_BOUND = ((-np.pi / 64, np.pi / 64),
(-np.pi / 64,
np.pi / 64), (-np.pi, np.pi))
self.TRANSLATION_AUGMENTATION_RATIO_BOUND = ((-0.2, 0.2),
(-0.2, 0.2), (0, 0))
self.voxelizer = Voxelizer(
voxel_size=self.VOXEL_SIZE,
clip_bound=self.CLIP_BOUND,
use_augmentation=augment_data,
scale_augmentation_bound=self.SCALE_AUGMENTATION_BOUND,
rotation_augmentation_bound=self.ROTATION_AUGMENTATION_BOUND,
translation_augmentation_ratio_bound=self.
TRANSLATION_AUGMENTATION_RATIO_BOUND,
ignore_label=True)
def transform_points_to_voxels(self,
data_dict=None,
config=None,
voxel_generator=None,
voxel_generator_2=None):
if data_dict is None:
try:
from spconv.utils import VoxelGeneratorV2 as VoxelGenerator
except:
from spconv.utils import VoxelGenerator
voxel_generator = VoxelGenerator(
voxel_size=config.VOXEL_SIZE,
point_cloud_range=self.point_cloud_range,
max_num_points=config.MAX_POINTS_PER_VOXEL,
max_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode])
#voxel_generator_2 = VoxelGenerator(
# voxel_size=config.VOXEL_SIZE,
# point_cloud_range=self.point_cloud_range,
# max_num_points=config.MAX_POINTS_PER_VOXEL,
# max_voxels=60000
#)
grid_size = (self.point_cloud_range[3:6] -
self.point_cloud_range[0:3]) / np.array(
config.VOXEL_SIZE)
self.grid_size = np.round(grid_size).astype(np.int64)
self.voxel_size = config.VOXEL_SIZE
return partial(self.transform_points_to_voxels,
voxel_generator=voxel_generator,
voxel_generator_2=voxel_generator_2)
points = data_dict['points']
points = data_dict['points_sp']
indices = data_dict['indices']
#print(points.shape)
"""
add code for visibility
"""
ori_points = points[:, [0, 1, 2, 4]]
#print(points[:,-1])
voxel_size = self.voxel_size
pc_range = self.point_cloud_range
#print(pc_range)
#print(self.voxel_size)
origins = data_dict['origins']
num_points = points.shape[0]
num_original = num_points
time_stamps = np.array([0], dtype=np.float32)
time_stamps = points[
indices[:-1],
-1] # counting on the fact we do not miss points from any intermediate time_stamps
time_stamps = (time_stamps[:-1] + time_stamps[1:]) / 2
time_stamps = [-1000.0] + time_stamps.tolist() + [1000.0
] # add boundaries
time_stamps = np.array(time_stamps)
num_original = indices[-1]
#print(time_stamps)
#print(points.shape)
#sys.exit()
if num_points > num_original:
#print("this is test sample")
original_points, sampled_points = ori_points[:
num_original, :], ori_points[
num_original:, :]
visibility, original_mask, sampled_mask = mapping.compute_logodds_and_masks(
original_points, sampled_points, origins, time_stamps,
pc_range, min(voxel_size))
points = np.concatenate(
(original_points[original_mask], sampled_points[sampled_mask]))
else:
visibility = mapping.compute_logodds(ori_points, origins,
time_stamps, pc_range, 0.2)
np.set_printoptions(threshold=sys.maxsize)
visi_map = np.zeros([512, 512, 3])
visibility = np.int64(visibility)
visibility = np.reshape(visibility, (40, 512, 512))[0:40, :, :]
visibility = np.transpose(visibility, (2, 1, 0))
#print(visibility)
#sys.exit()
mask_occ = (visibility >= 1).nonzero()
#print(mask_occ)
mask_free = (visibility == 0).nonzero()
mask_unknown = (visibility == -1).nonzero()
visi_map[np.int64(mask_free[0]),
np.int64(mask_free[1]), :] = np.array([255, 0, 0]) / 255
visi_map[np.int64(mask_occ[0]),
np.int64(mask_occ[1]), :] = np.array([0, 255, 0]) / 255
visi_map[mask_unknown[0],
mask_unknown[1], :] = np.array([0, 0, 255]) / 255
#print(.shape)
#visibility = np.pad(visibility, ((0,2),(0,0)), 'edge')
data_dict['vis'] = visibility
#print(data_dict.keys())
dense_points = data_dict['dense_point']
points = data_dict['points']
#print(points.shape)
voxel_output = voxel_generator.generate(points)
#voxel_dense = voxel_generator.generate(dense_points)
#print(voxel_dense[...,-1])
#print(voxel_output['voxels'].shape)
#sys.exit()
if isinstance(voxel_output, dict):
voxels, coordinates, num_points = \
voxel_output['voxels'], voxel_output['coordinates'], voxel_output['num_points_per_voxel']
else:
voxels, coordinates, num_points = voxel_output
if not data_dict['use_lead_xyz']:
voxels = voxels[..., 3:] # remove xyz in voxels(N, 3)
#data_dict['dense_pillar'] = voxel_dense['voxels']
#data_dict['dense_pillar_coords'] = voxel_dense['coordinates']
data_dict['voxels'] = voxels
data_dict['voxel_coords'] = coordinates
data_dict['voxel_num_points'] = num_points
return data_dict