def read_fn(model, filename):
BLOCK_SIZE = 3.0
BLOCK_STRIDE = 1.5
SAMPLE_STRIDE = 0.1
RESAMPLE_RATIO_LOW = 0.8
RESAMPLE_RATIO_HIGH = 1.0
NEIGHBOR_RADIUS = 0.2
MIN_POINT_NUM = 2048
points, labels = read_room_pkl(filename) # [n,6],[n,1]
if model == 'train':
xyzs, rgbs, covars, lbls = sample_block(points,
labels,
SAMPLE_STRIDE,
BLOCK_SIZE,
BLOCK_STRIDE,
min_pn=MIN_POINT_NUM,
use_rescale=True,
use_flip=True,
use_rotate=False)
xyzs, rgbs, covars, lbls, nidxs, nidxs_lens, nidxs_bgs, cidxs, block_bgs, block_lens = \
normalize_block(xyzs,rgbs,covars,lbls,neighbor_radius=NEIGHBOR_RADIUS,resample=True,jitter_color=True,
resample_low=RESAMPLE_RATIO_LOW,resample_high=RESAMPLE_RATIO_HIGH)
else:
xyzs, rgbs, covars, lbls = sample_block(points,
labels,
SAMPLE_STRIDE,
BLOCK_SIZE,
BLOCK_SIZE,
min_pn=MIN_POINT_NUM / 2)
xyzs, rgbs, covars, lbls, nidxs, nidxs_lens, nidxs_bgs, cidxs, block_bgs, block_lens = \
normalize_block(xyzs,rgbs,covars,lbls,neighbor_radius=NEIGHBOR_RADIUS)
return xyzs, rgbs, covars, lbls, nidxs, nidxs_lens, nidxs_bgs, cidxs, block_bgs, block_lens
def test_time():
from draw_util import output_points, get_class_colors
from sklearn.cluster import KMeans
colors = get_class_colors()
train_list, test_list = get_block_train_test_split()
random.shuffle(train_list)
train_list = ['data/S3DIS/room_block_10_10/' + fn for fn in train_list]
# filename=train_list[0]
filename = 'data/S3DIS/room_block_10_10/49_Area_1_office_8.pkl'
points, labels = read_room_pkl(filename) # [n,6],[n,1]
for i in xrange(10):
t = time.time()
xyzs, rgbs, covars, lbls = sample_block(points,
labels,
0.1,
3.0,
1.5,
min_pn=2048,
use_rescale=True,
use_flip=True,
use_rotate=True)
print 'sample block cost {} s '.format(time.time() - t)
t = time.time()
xyzs, rgbs, covars, lbls, nidxs, nidxs_lens, nidxs_bgs, cidxs=\
normalize_block(xyzs,rgbs,covars,lbls,0.2,True,0.8,1.0,True,2.5)
print 'normalize cost {} s '.format(time.time() - t)
def test_normalize():
from draw_util import output_points, get_class_colors
from sklearn.cluster import KMeans
colors = get_class_colors()
train_list, test_list = get_block_train_test_split()
random.shuffle(train_list)
train_list = ['data/S3DIS/room_block_10_10/' + fn for fn in train_list]
# filename=train_list[0]
filename = 'data/S3DIS/room_block_10_10/49_Area_1_office_8.pkl'
points, labels = read_room_pkl(filename) # [n,6],[n,1]
begin = time.time()
xyzs, rgbs, covars, lbls = sample_block(points,
labels,
SAMPLE_STRIDE,
BLOCK_SIZE,
BLOCK_STRIDE,
min_pn=2048,
use_rescale=True,
use_flip=True,
use_rotate=True)
print 'sample_block cost {} s'.format(time.time() - begin)
# for j in xrange(len(xyzs)):
# print np.min(xyzs[j],axis=0),np.max(xyzs[j],axis=0)
# print np.min(rgbs[j],axis=0),np.max(rgbs[j],axis=0)
# print xyzs[j].shape,lbls[j].shape
# output_points('test_result/label_init{}.txt'.format(j),xyzs[j],colors[lbls[j].flatten(),:])
# output_points('test_result/lrgbs_init{}.txt'.format(j),xyzs[j],rgbs[j])
xyzs, rgbs, covars, lbls, nidxs, nidxs_lens, nidxs_bgs, cidxs=\
normalize_block(xyzs,rgbs,covars,lbls,0.2,True,0.8,1.0,True,2.5)
for j in xrange(len(xyzs)):
print xyzs[j].shape, rgbs[j].shape, covars[j].shape, lbls[
j].shape, nidxs[j].shape, nidxs_lens[j].shape, nidxs_bgs[
j].shape, cidxs[j].shape
print np.min(xyzs[j], axis=0), np.max(xyzs[j], axis=0)
print np.min(rgbs[j], axis=0), np.max(rgbs[j], axis=0)
print 'avg nn size: {}'.format(len(nidxs[j]) / float(len(xyzs[j])))
# print xyzs[j].shape,lbls[j].shape
output_points('test_result/label{}.txt'.format(j), xyzs[j],
colors[lbls[j].flatten(), :])
output_points('test_result/lrgbs{}.txt'.format(j), xyzs[j],
np.asarray(rgbs[j] * 128 + 127, np.int32))
for j in xrange(len(xyzs[0])):
output_points(
'test_result/nn{}.txt'.format(j),
xyzs[0][nidxs[0][nidxs_bgs[0][j]:nidxs_bgs[0][j] +
nidxs_lens[0][j]], :])
def test_sample():
from draw_util import output_points, get_class_colors
from sklearn.cluster import KMeans
colors = get_class_colors()
train_list, test_list = get_block_train_test_split()
random.shuffle(train_list)
train_list = ['data/S3DIS/room_block_10_10/' + fn for fn in train_list]
filename = train_list[0]
# filename='data/S3DIS/room_block_10_10/58_Area_2_auditorium_2.pkl'
points, labels = read_room_pkl(filename) # [n,6],[n,1]
print np.min(points, axis=0)
begin = time.time()
xyzs, rgbs, covars, lbls = sample_block(points,
labels,
0.075,
1.5,
1.5,
min_pn=2048 / 2)
#use_rescale=True,use_flip=True,use_rotate=True)
print 'sample_block cost {} s'.format(time.time() - begin)
print np.min(np.concatenate(xyzs, axis=0), axis=0)
kc = np.random.randint(0, 255, [5, 3])
for j in xrange(len(xyzs)):
# print xyzs[j].shape,lbls[j].shape
output_points('test_result/label{}.txt'.format(j), xyzs[j],
colors[lbls[j].flatten(), :])
output_points('test_result/lrgbs{}.txt'.format(j), xyzs[j], rgbs[j])
kmeans = KMeans(5)
preds = kmeans.fit_predict(np.concatenate(covars, axis=0))
output_points('test_result/kmeans.txt', np.concatenate(xyzs, axis=0),
kc[preds.flatten(), :])
pt_num = [len(xyz) for xyz in xyzs]
print 'avg pt num: {}'.format(np.mean(pt_num))
def read_fn_hierarchy(model,
filename,
presample=True,
use_rotate=False,
nr1=0.1,
nr2=0.4,
nr3=1.0,
vc1=0.2,
vc2=0.5,
sstride=0.075,
bsize=3.0,
bstride=1.5,
min_pn=1024,
resample_ratio_low=0.8,
resample_ratio_high=1.0,
covar_ds_stride=0.03,
covar_nn_size=0.1,
max_pt_num=10240):
if filename.endswith('.pkl'):
points, labels = read_room_pkl(filename) # [n,6],[n,1]
else:
points, labels = read_room_h5(filename) # [n,6],[n,1]
if model == 'train':
if presample:
xyzs, rgbs, covars, lbls = sample_block_v2(
points,
labels,
sstride,
bsize,
bstride,
min_pn=min_pn,
use_rescale=True,
use_flip=True,
use_rotate=use_rotate,
covar_nn_size=covar_nn_size)
else:
xyzs, rgbs, covars, lbls = sample_block(
points,
labels,
sstride,
bsize,
bstride,
min_pn=min_pn,
use_rescale=True,
use_flip=True,
use_rotate=use_rotate,
covar_ds_stride=covar_ds_stride,
covar_nn_size=covar_nn_size)
cxyzs, dxyzs, rgbs, covars, lbls, vlens, vlens_bgs, vcidxs, cidxs, nidxs, nidxs_bgs, nidxs_lens, block_mins = \
normalize_block_hierarchy(xyzs,rgbs,covars,lbls,bsize=bsize,nr1=nr1,nr2=nr2,nr3=nr3,vc1=vc1,vc2=vc2,
resample=True,jitter_color=True,
resample_low=resample_ratio_low,resample_high=resample_ratio_high,
max_pt_num=max_pt_num)
else:
if presample:
xyzs, rgbs, covars, lbls = sample_block_v2(
points,
labels,
sstride,
bsize,
bsize,
min_pn=min_pn / 2,
covar_nn_size=covar_nn_size)
else:
xyzs, rgbs, covars, lbls = sample_block(
points,
labels,
sstride,
bsize,
bsize,
min_pn=min_pn / 2,
covar_ds_stride=covar_ds_stride,
covar_nn_size=covar_nn_size)
cxyzs, dxyzs, rgbs, covars, lbls, vlens, vlens_bgs, vcidxs, cidxs, nidxs, nidxs_bgs, nidxs_lens, block_mins = \
normalize_block_hierarchy(xyzs,rgbs,covars,lbls,bsize=bsize,nr1=nr1,nr2=nr2,nr3=nr3,vc1=vc1,vc2=vc2,
max_pt_num=max_pt_num)
return cxyzs, dxyzs, rgbs, covars, lbls, vlens, vlens_bgs, vcidxs, cidxs, nidxs, nidxs_bgs, nidxs_lens, block_mins