def __getitem__(self, index):
# get item in tensor shape
scan_file = self.scan_files[index]
if self.gt:
label_file = self.label_files[index]
# open a semantic laserscan
if self.gt:
scan = SemLaserScan(self.color_map,
project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down)
else:
scan = LaserScan(project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down)
# open and obtain scan
scan.open_scan(scan_file)
if self.gt:
scan.open_label(label_file)
# map unused classes to used classes (also for projection)
scan.sem_label = self.map(scan.sem_label, self.learning_map)
scan.proj_sem_label = self.map(scan.proj_sem_label,
self.learning_map)
# make a tensor of the uncompressed data (with the max num points)
unproj_n_points = scan.points.shape[0]
unproj_xyz = torch.full((self.max_points, 3), -1.0, dtype=torch.float)
unproj_xyz[:unproj_n_points] = torch.from_numpy(scan.points)
unproj_range = torch.full([self.max_points], -1.0, dtype=torch.float)
unproj_range[:unproj_n_points] = torch.from_numpy(scan.unproj_range)
unproj_remissions = torch.full([self.max_points],
-1.0,
dtype=torch.float)
unproj_remissions[:unproj_n_points] = torch.from_numpy(scan.remissions)
if self.gt:
unproj_labels = torch.full([self.max_points],
-1.0,
dtype=torch.int32)
unproj_labels[:unproj_n_points] = torch.from_numpy(scan.sem_label)
else:
unproj_labels = []
# get points and labels
proj_range = torch.from_numpy(scan.proj_range).clone()
proj_xyz = torch.from_numpy(scan.proj_xyz).clone()
proj_remission = torch.from_numpy(scan.proj_remission).clone()
proj_mask = torch.from_numpy(scan.proj_mask)
if self.gt:
proj_labels = torch.from_numpy(scan.proj_sem_label).clone()
proj_labels = proj_labels * proj_mask
else:
proj_labels = []
proj_x = torch.full([self.max_points], -1, dtype=torch.long)
proj_x[:unproj_n_points] = torch.from_numpy(scan.proj_x)
proj_y = torch.full([self.max_points], -1, dtype=torch.long)
proj_y[:unproj_n_points] = torch.from_numpy(scan.proj_y)
proj = torch.cat([
proj_range.unsqueeze(0).clone(),
proj_xyz.clone().permute(2, 0, 1),
proj_remission.unsqueeze(0).clone()
])
proj = (proj - self.sensor_img_means[:, None, None]
) / self.sensor_img_stds[:, None, None]
proj = proj * proj_mask.float()
# get name and sequence
path_norm = os.path.normpath(scan_file)
path_split = path_norm.split(os.sep)
path_seq = path_split[-3]
path_name = path_split[-1].replace(".bin", ".label")
# print("path_norm: ", path_norm)
# print("path_seq", path_seq)
# print("path_name", path_name)
# return
return proj, proj_mask, proj_labels, unproj_labels, path_seq, path_name, proj_x, proj_y, proj_range, unproj_range, proj_xyz, unproj_xyz, proj_remission, unproj_remissions, unproj_n_points
def __getitem__(self, index):
# get item in tensor shape
scan_file = self.scan_files[index]
# JLLIU
# print(scan_file)
if self.gt:
label_file = self.label_files[index]
# open a semantic laserscan
DA = False
flip_sign = False
rot = False
drop_points = False
if self.transform:
if random.random() > 0.5:
if random.random() > 0.5:
DA = True
if random.random() > 0.5:
flip_sign = True
if random.random() > 0.5:
rot = True
drop_points = random.uniform(0, 0.5)
if self.gt:
scan = SemLaserScan(self.color_map,
project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down,
DA=DA,
flip_sign=flip_sign,
drop_points=drop_points)
else:
scan = LaserScan(project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down,
DA=DA,
rot=rot,
flip_sign=flip_sign,
drop_points=drop_points)
# open and obtain scan
scan.open_scan(scan_file)
if self.gt:
scan.open_label(label_file)
# map unused classes to used classes (also for projection)
scan.sem_label = self.map(scan.sem_label, self.learning_map)
scan.proj_sem_label = self.map(scan.proj_sem_label,
self.learning_map)
#print("proj_x.shape: ",proj_x.shape)
#print("proj_y.shape: ",proj_y.shape)
# make a tensor of the uncompressed data (with the max num points)
unproj_n_points = scan.points.shape[0]
unproj_xyz = torch.full((self.max_points, 3), -1.0, dtype=torch.float)
unproj_xyz[:unproj_n_points] = torch.from_numpy(scan.points)
unproj_range = torch.full([self.max_points], -1.0, dtype=torch.float)
unproj_range[:unproj_n_points] = torch.from_numpy(scan.unproj_range)
unproj_remissions = torch.full([self.max_points],
-1.0,
dtype=torch.float)
unproj_remissions[:unproj_n_points] = torch.from_numpy(scan.remissions)
if self.gt:
unproj_labels = torch.full([self.max_points],
-1.0,
dtype=torch.int32)
unproj_labels[:unproj_n_points] = torch.from_numpy(scan.sem_label)
else:
unproj_labels = []
# JLLIU:
# 底下的 proj_xyz.shape: torch.Size([64, 2048, 3]) 就是之前在 laserscan.py 看到的那個
# intensity 的 proj_remission[proj_y, proj_x] 也是
"""
seq_now = os.path.normpath(scan_file).split(os.sep)[-3]
file_now = os.path.normpath(scan_file).split(os.sep)[-1].replace(".bin", ".npy")
proj_xyzi = np.zeros(shape=(64,2048,4))
proj_xyzi[:,:,0:3] = scan.proj_xyz
proj_xyzi[:,:,3] = scan.proj_remission
np.save('/home/doggy/SalsaNext/train/tasks/semantic/dataset/xyzi_npy/'+ seq_now + '/' + file_now , proj_xyzi)
print("\nnpy_name: ", file_now)
print("proj_xyz[50,50]: ", scan.proj_xyz[50,50])
print("proj_i[50,50]: ", scan.proj_remission[50,50])
print("proj_xyzi[50,50]: ", proj_xyzi[50,50])
"""
# get points and labels
proj_range = torch.from_numpy(scan.proj_range).clone()
proj_xyz = torch.from_numpy(scan.proj_xyz).clone()
proj_remission = torch.from_numpy(scan.proj_remission).clone()
proj_mask = torch.from_numpy(scan.proj_mask)
if self.gt:
proj_labels = torch.from_numpy(scan.proj_sem_label).clone()
proj_labels = proj_labels * proj_mask
else:
proj_labels = []
proj_x = torch.full([self.max_points], -1, dtype=torch.long)
proj_x[:unproj_n_points] = torch.from_numpy(scan.proj_x)
proj_y = torch.full([self.max_points], -1, dtype=torch.long)
proj_y[:unproj_n_points] = torch.from_numpy(scan.proj_y)
proj = torch.cat([
proj_range.unsqueeze(0).clone(),
proj_xyz.clone().permute(2, 0, 1),
proj_remission.unsqueeze(0).clone()
])
proj = (proj - self.sensor_img_means[:, None, None]
) / self.sensor_img_stds[:, None, None]
proj = proj * proj_mask.float()
# get name and sequence
path_norm = os.path.normpath(scan_file)
path_split = path_norm.split(os.sep)
path_seq = path_split[-3]
path_name = path_split[-1].replace(".bin", ".label")
# return
return proj, proj_mask, proj_labels, unproj_labels, path_seq, path_name, proj_x, proj_y, proj_range, unproj_range, proj_xyz, unproj_xyz, proj_remission, unproj_remissions, unproj_n_points
def __getitem__(self, index):
# get item in tensor shape
scan_file = self.scan_files[index]
if self.gt:
label_file = self.label_files[index]
# open a semantic laserscan
DA = False
flip_sign = False
rot = False
drop_points = False
if self.transform:
if random.random() > 0.5:
if random.random() > 0.5:
DA = True
if random.random() > 0.5:
flip_sign = True
if random.random() > 0.5:
rot = True
drop_points = random.uniform(0, 0.5)
if self.gt:
scan = SemLaserScan(self.color_map,
project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down,
DA=DA,
flip_sign=flip_sign,
drop_points=drop_points)
else:
scan = LaserScan(project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down,
DA=DA,
rot=rot,
flip_sign=flip_sign,
drop_points=drop_points)
# open and obtain scan
scan.open_scan(scan_file)
if self.gt:
scan.open_label(label_file)
# map unused classes to used classes (also for projection)
scan.sem_label = self.map(scan.sem_label, self.learning_map)
scan.proj_sem_label = self.map(scan.proj_sem_label, self.learning_map)
# get points and labels
proj_range = torch.from_numpy(scan.proj_range).clone()
proj_segment_angle = torch.from_numpy(scan.segment_angle).clone()
proj_xyz = torch.from_numpy(scan.proj_xyz).clone()
proj_remission = torch.from_numpy(scan.proj_remission).clone()
proj_mask = torch.from_numpy(scan.proj_mask)
if self.gt:
proj_labels = torch.from_numpy(scan.proj_sem_label).clone()
proj_labels = proj_labels * proj_mask
else:
proj_labels = []
# return
return proj_range, proj_segment_angle, proj_xyz, proj_remission, proj_mask, proj_labels, scan.points, scan_file, scan.sem_label
def __getitem__(self, index):
# get item in tensor shape
scan_file = self.scan_files[index]
if self.gt:
label_file = self.label_files[index]
# open a semantic laserscan
if self.gt:
scan = SemLaserScan(self.color_map,
project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down)
else:
scan = LaserScan(project=True,
H=self.sensor_img_H,
W=self.sensor_img_W,
fov_up=self.sensor_fov_up,
fov_down=self.sensor_fov_down)
# open and obtain scan
scan.open_scan(scan_file)
if self.gt:
scan.open_label(label_file)
# map unused classes to used classes (also for projection)
scan.sem_label = self.map(scan.sem_label, self.learning_map)
scan.proj_sem_label = self.map(scan.proj_sem_label,
self.learning_map)
# make a tensor of the uncompressed data (with the max num points)
unproj_n_points = scan.points.shape[0]
unproj_xyz = torch.full((self.max_points, 3), -1.0, dtype=torch.float)
unproj_xyz[:unproj_n_points] = torch.from_numpy(scan.points)
unproj_range = torch.full([self.max_points], -1.0, dtype=torch.float)
unproj_range[:unproj_n_points] = torch.from_numpy(scan.unproj_range)
unproj_remissions = torch.full([self.max_points],
-1.0,
dtype=torch.float)
unproj_remissions[:unproj_n_points] = torch.from_numpy(scan.remissions)
if self.gt:
unproj_labels = torch.full([self.max_points],
-1.0,
dtype=torch.int32)
unproj_labels[:unproj_n_points] = torch.from_numpy(scan.sem_label)
else:
unproj_labels = []
# get points and labels
proj_range = torch.from_numpy(scan.proj_range).clone()
proj_xyz = torch.from_numpy(scan.proj_xyz).clone()
proj_remission = torch.from_numpy(scan.proj_remission).clone()
proj_mask = torch.from_numpy(scan.proj_mask)
if self.gt:
proj_labels = torch.from_numpy(scan.proj_sem_label).clone()
proj_labels = proj_labels * proj_mask
else:
proj_labels = []
proj_x = torch.full([self.max_points], -1, dtype=torch.long)
proj_x[:unproj_n_points] = torch.from_numpy(scan.proj_x)
proj_y = torch.full([self.max_points], -1, dtype=torch.long)
proj_y[:unproj_n_points] = torch.from_numpy(scan.proj_y)
proj = torch.cat([
proj_range.unsqueeze(0).clone(),
proj_xyz.clone().permute(2, 0, 1),
proj_remission.unsqueeze(0).clone()
])
proj_blocked = proj.unsqueeze(1) # Swap Batch and channel dimensions
proj = (proj - self.sensor_img_means[:, None, None]
) / self.sensor_img_stds[:, None, None]
proj = proj * proj_mask.float()
# get name and sequence
path_norm = os.path.normpath(scan_file)
path_split = path_norm.split(os.sep)
path_seq = path_split[-3]
path_name = path_split[-1].replace(".bin", ".label")
# print("path_norm: ", path_norm)
# print("path_seq", path_seq)
# print("path_name", path_name)
# import time
# import cv2
# cv2.imwrite('/home/snowflake/Desktop/big8192-128.png', proj_blocked[0,0, :, :].numpy()*15)
# print('proj_blocked.shape')
# print(proj_blocked.shape)
# time.sleep(1000)
n, c, h, w = proj_blocked.size()
proj2 = proj.clone()
proj = proj.unsqueeze(0)
mask_image = proj_mask.unsqueeze(0).unsqueeze(0).float()
downsamplings = 4
representations = {}
representations['image'] = []
representations['points'] = []
windows_size = 3 # windows size
for i in range(downsamplings):
proj_chan_group_points = f.unfold(proj_blocked,
kernel_size=3,
stride=1,
padding=1)
projmask_chan_group_points = f.unfold(mask_image,
kernel_size=3,
stride=1,
padding=1)
# Get the mean point (taking apart non-valid points)
proj_chan_group_points_sum = torch.sum(proj_chan_group_points,
dim=1)
projmask_chan_group_points_sum = torch.sum(
projmask_chan_group_points, dim=1)
proj_chan_group_points_mean = proj_chan_group_points_sum / projmask_chan_group_points_sum
# tile it for being able to substract it to the other points
tiled_proj_chan_group_points_mean = proj_chan_group_points_mean.unsqueeze(
1).repeat(1, windows_size * windows_size, 1)
# remove nans due to empty blocks
is_nan = tiled_proj_chan_group_points_mean != tiled_proj_chan_group_points_mean
tiled_proj_chan_group_points_mean[is_nan] = 0.
# compute valid mask per point
tiled_projmask_chan_group_points = (
1 - projmask_chan_group_points.repeat(n, 1, 1)).byte()
# substract mean point to points
proj_chan_group_points_relative = proj_chan_group_points - tiled_proj_chan_group_points_mean
# set to zero points which where non valid at the beginning
proj_chan_group_points_relative[
tiled_projmask_chan_group_points] = 0.
# compute distance (radius) to mean point
# xyz_relative = proj_chan_group_points_relative[1:4,...]
# relative_distance = torch.norm(xyz_relative, dim=0).unsqueeze(0)
# NOW proj_chan_group_points_relative HAS Xr, Yr, Zr, Rr, Dr relative to the mean point
proj_norm_chan_group_points = f.unfold(proj.permute(1, 0, 2, 3),
kernel_size=3,
stride=1,
padding=1)
# NOW proj_norm_chan_group_points HAS X, Y, Z, R, D. Now we have to concat them both
proj_chan_group_points_combined = torch.cat(
[proj_norm_chan_group_points, proj_chan_group_points_relative],
dim=0)
# convert back to image for image-convolution-branch
proj_out = f.fold(proj_chan_group_points_combined,
proj_blocked.shape[-2:],
kernel_size=3,
stride=1,
padding=1)
proj_out = proj_out.squeeze(1)
proj = nn.functional.interpolate(proj,
size=(int(proj.shape[2] / 2),
int(proj.shape[3] / 2)),
mode='nearest')
proj_blocked = nn.functional.interpolate(
proj_blocked.permute(1, 0, 2, 3),
size=(int(proj_blocked.shape[2] / 2),
int(proj_blocked.shape[3] / 2)),
mode='nearest').permute(1, 0, 2, 3)
mask_image = nn.functional.interpolate(
mask_image,
size=(int(mask_image.shape[2] / 2),
int(mask_image.shape[3] / 2)),
mode='nearest')
representations['points'].append(proj_chan_group_points_combined)
representations['image'].append(proj_out)
# print('append' +str(i))
#
# print(proj_chan_group_points_combined.shape)
# print(proj_out.shape)
return proj2, proj_mask, proj_labels, unproj_labels, path_seq, path_name, proj_x, proj_y, proj_range, unproj_range, proj_xyz, unproj_xyz, proj_remission, unproj_remissions, unproj_n_points, representations