def __call__(self, load_index):
if self.aug:
ret = aug_data(self.data_tag[load_index],
self.data_dir,
sampler=self.db_sampler)
else:
rgb = cv2.resize(cv2.imread(self.f_rgb[load_index]),
(cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT))
raw_lidar = np.fromfile(self.f_lidar[load_index],
dtype=np.float32).reshape((-1, 4))
if not self.is_testset:
labels = [
line for line in open(self.f_label[load_index],
'r').readlines()
]
else:
labels = ['']
tag = self.data_tag[load_index]
if self.f_voxel is None:
voxel = process_pointcloud(tag, raw_lidar)
else:
voxel_files = np.load(self.f_voxel[load_index])
voxel = {}
voxel['feature_buffer'] = voxel_files['feature_buffer']
voxel['coordinate_buffer'] = voxel_files['coordinate_buffer']
voxel['number_buffer'] = voxel_files['number_buffer']
voxel['mask_buffer'] = voxel_files['mask_buffer']
ret = [tag, rgb, raw_lidar, voxel, labels]
return ret
def __call__(self, load_index):
if aug:
ret = aug_data(self.data_tag[load_index], self.data_dir)
tag.append(ret[0])
rgb.append(ret[1])
raw_lidar.append(ret[2])
voxel.append(ret[3])
labels.append(ret[4])
else:
rgb.append(
cv2.resize(cv2.imread(f_rgb[load_index]),
(cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT)))
raw_lidar.append(
np.fromfile(f_lidar[load_index], dtype=np.float32).reshape(
(-1, 4)))
if not is_testset:
labels.append([
line
for line in open(f_label[load_index], 'r').readlines()
])
else:
labels.append([''])
tag.append(data_tag[load_index])
voxel.append(process_pointcloud(raw_lidar[-1]))
return n
def __call__(self, load_index):
if self.aug:
ret = aug_data(self.data_tag[load_index], self.data_dir)
else:
#rgb = cv2.resize(cv2.imread(self.f_rgb[load_index]), (cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT))
rgb = 0 # placeholder
rgb = cv2.resize(
cv2.imread(
'/home/ziyanw1/data/KITTI/training/image_2/001201.png'),
(cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT))
#rgb.append( cv2.imread(f_rgb[load_index]) )
raw_lidar = np.fromfile(self.f_lidar[load_index],
dtype=np.float32).reshape((-1, 4))
raw_obj_pc = np.fromfile(self.f_obj[load_index],
dtype=np.float32).reshape((-1, 4))
if not self.is_testset:
labels = [
line for line in open(self.f_label[load_index],
'r').readlines()
]
else:
labels = ['']
tag = self.data_tag[load_index]
voxel = process_pointcloud(raw_lidar)
ret = [tag, rgb, raw_lidar, raw_obj_pc, voxel, labels]
return ret
def fill_queue(self, batch_size=0):
load_index = self.load_index
self.load_index += batch_size
if self.load_index >= self.dataset_size:
if not self.is_testset: # test set just end
if self.require_shuffle:
self.shuffle_dataset()
load_index = 0
self.load_index = load_index + batch_size
else:
self.work_exit.value = True
labels, tag, voxel, rgb, raw_lidar = [], [], [], [], []
for _ in range(batch_size):
try:
if self.aug:
ret = aug_data(self.data_tag[load_index], self.object_dir)
tag.append(ret[0])
rgb.append(ret[1])
raw_lidar.append(ret[2])
voxel.append(ret[3])
labels.append(ret[4])
else:
rgb.append(cv2.resize(cv2.imread(
self.f_rgb[load_index]), (cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT)))
raw_lidar.append(np.fromfile(
self.f_lidar[load_index], dtype=np.float32).reshape((-1, 4)))
if not self.is_testset:
labels.append([line for line in open(
self.f_label[load_index], 'r').readlines()])
else:
#labels.append(['Dummy 0.00 0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0'])
labels.append([''])
tag.append(self.data_tag[load_index])
voxel.append(process_pointcloud(raw_lidar[-1]))
load_index += 1
except:
if not self.is_testset: # test set just end
self.load_index = 0
if self.require_shuffle:
self.shuffle_dataset()
else:
self.work_exit.value = True
# only for voxel -> [gpu, k_single_batch, ...]
vox_feature, vox_number, vox_coordinate = [], [], []
single_batch_size = int(self.batch_size / self.multi_gpu_sum)
for idx in range(self.multi_gpu_sum):
_, per_vox_feature, per_vox_number, per_vox_coordinate = build_input(
voxel[idx * single_batch_size:(idx + 1) * single_batch_size])
vox_feature.append(per_vox_feature)
vox_number.append(per_vox_number)
vox_coordinate.append(per_vox_coordinate)
self.dataset_queue.put_nowait(
(labels, (vox_feature, vox_number, vox_coordinate), rgb, raw_lidar, tag))
def __call__(self,load_index):
if self.aug:
ret = aug_data(self.data_tag[load_index], self.data_dir)
else:
rgb = cv2.resize(cv2.imread(self.f_rgb[load_index]), (cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT))
raw_lidar = np.fromfile(self.f_lidar[load_index], dtype=np.float32).reshape((-1, 4))
if not self.is_testset:
labels = [line for line in open(self.f_label[load_index], 'r').readlines()]
else:
labels = ['']
tag = self.data_tag[load_index]
voxel = process_pointcloud(raw_lidar)
ret = [tag, rgb, raw_lidar, voxel, labels]
return ret
def test_aug_data():
tag = '%06d' % (12)
root_path = '/mine/KITTI_DAT/'
object_dir = os.path.join(root_path, 'training')
info_path = os.path.join(root_path, 'kitti_dbinfos_train.pkl')
db_sampler = DataBaseSampler(root_path, info_path)
tag, rgb, lidar, voxel_dict, label = aug_data(tag,
object_dir,
sampler=db_sampler)
print(lidar.shape)
print(label)
gt_box3d = label_to_gt_box3d([tag],
np.array(label)[np.newaxis, :],
cls='',
coordinate='lidar')[0]
gt_box3d_corners = center_to_corner_box3d(gt_box3d)
view_pc(lidar, gt_box3d_corners)
def load(self, batch_size=1):
if self.load_index >= self.dataset_size:
return None
num_to_load = batch_size
labels, tag, voxel, rgb, raw_lidar = [], [], [], [], []
vox_feature, vox_number, vox_coordinate = [], [], []
# Load normal data
for i in range(batch_size):
load_index = self.load_index + i
rgb.append(
cv2.resize(cv2.imread(self.f_rgb[load_index]),
(cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT)))
raw_lidar.append(
np.fromfile(self.f_lidar[load_index],
dtype=np.float32).reshape((-1, 4)))
if not self.is_testset:
labels.append([
line for line in open(self.f_label[load_index],
'r').readlines()
])
else:
labels.append([''])
tag.append(self.data_tag[load_index])
voxel.append(process_pointcloud(raw_lidar[-1]))
bsize, per_vox_feat, per_vox_num, per_vox_coor = build_input(
[voxel[-1]])
vox_feature.append(per_vox_feat)
vox_number.append(per_vox_num)
vox_coordinate.append(per_vox_coor)
#print('bsize', bsize)
#print('vox_feature', np.array(vox_feature).shape)
#print('vox_number', vox_number)
# Create augmented data
augIdxs, aug_voxel = [], []
if self.aug and not self.is_testset:
num_to_load += self.aug_num
# Get the indices of members to be augmented
augIdxs = np.random.choice(np.arange(
self.load_index, self.load_index + batch_size + 1),
self.aug_num,
replace=False)
for idx in augIdxs:
ret = aug_data(self.data_tag[idx], self.object_dir)
tag.append(ret[0])
rgb.append(ret[1])
raw_lidar.append(ret[2])
aug_voxel.append(ret[3])
labels.append(ret[4])
bsize, per_vox_feat, per_vox_coor, per_vox_num = build_input(
[aug_voxel[-1]])
vox_feature.append(per_vox_feat)
#print('per_vox_feat', np.array(per_vox_feat).shape)
vox_number.append(per_vox_num)
vox_coordinate.append(per_vox_coor)
#print('bsize', bsize)
#print('vox_feature', np.array(vox_feature).shape)
ret = (np.array(tag), np.array(labels), np.array(vox_feature),
np.array(vox_number), np.array(vox_coordinate), np.array(rgb),
np.array(raw_lidar))
flag = False
self.load_index += batch_size
if self.load_index >= self.dataset_size:
flag = True
return flag, ret
def iterate_data(data_dir,
shuffle=False,
aug=False,
is_testset=False,
batch_size=1,
multi_gpu_sum=1):
f_rgb = glob.glob(os.path.join(data_dir, 'image_2', '*.png'))
f_lidar = glob.glob(os.path.join(data_dir, 'velodyne', '*.bin'))
f_label = glob.glob(os.path.join(data_dir, 'label_2', '*.txt'))
f_rgb.sort()
f_lidar.sort()
f_label.sort()
data_tag = [name.split('/')[-1].split('.')[-2] for name in f_rgb]
assert len(data_tag) != 0, "dataset folder is not correct"
assert len(data_tag) == len(f_rgb) == len(
f_lidar), "dataset folder is not correct"
nums = len(f_rgb)
indices = list(range(nums))
if shuffle:
np.random.shuffle(indices)
num_batches = int(math.floor(nums / float(batch_size)))
for batch_idx in range(num_batches):
start_idx = batch_idx * batch_size
excerpt = indices[start_idx:start_idx + batch_size]
labels, tag, voxel, rgb, raw_lidar = [], [], [], [], []
for load_index in excerpt:
if aug:
ret = aug_data(data_tag[load_index], data_dir)
tag.append(ret[0])
rgb.append(ret[1])
raw_lidar.append(ret[2])
voxel.append(ret[3])
labels.append(ret[4])
else:
rgb.append(
cv2.resize(cv2.imread(f_rgb[load_index]),
(cfg.IMAGE_WIDTH, cfg.IMAGE_HEIGHT)))
#rgb.append( cv2.imread(f_rgb[load_index]) )
raw_lidar.append(
np.fromfile(f_lidar[load_index], dtype=np.float32).reshape(
(-1, 4)))
if not is_testset:
labels.append([
line
for line in open(f_label[load_index], 'r').readlines()
])
else:
labels.append([''])
tag.append(data_tag[load_index])
voxel.append(process_pointcloud(raw_lidar[-1]))
# only for voxel -> [gpu, k_single_batch, ...]
vox_feature, vox_number, vox_coordinate = [], [], []
single_batch_size = int(batch_size / multi_gpu_sum)
for idx in range(multi_gpu_sum):
_, per_vox_feature, per_vox_number, per_vox_coordinate = build_input(
voxel[idx * single_batch_size:(idx + 1) * single_batch_size])
vox_feature.append(per_vox_feature)
vox_number.append(per_vox_number)
vox_coordinate.append(per_vox_coordinate)
ret = (np.array(tag), np.array(labels), np.array(vox_feature),
np.array(vox_number), np.array(vox_coordinate), np.array(rgb),
np.array(raw_lidar))
yield ret
def _augmentation(self, tag, rgb, raw_lidar, voxel, labels):
return aug_data(tag, rgb, raw_lidar, voxel, labels)
