def prepare_s3dis_train_single_file(fn):
in_fn = 'data/S3DIS/room_block_10_10/' + fn
all_data = [[] for _ in xrange(5)]
bg = time.time()
data = prepare_data(in_fn, True, True, False, False, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, True, True, False, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, True, False, True, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, True, True, True, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, False, False, False, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, False, True, False, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, False, False, True, True, True)
for t in xrange(5):
all_data[t] += data[t]
data = prepare_data(in_fn, True, False, True, True, True, True)
for t in xrange(5):
all_data[t] += data[t]
out_fn = 'data/S3DIS/sampled_train_nolimits/' + fn
save_pkl(out_fn, all_data)
print 'done {} cost {} s'.format(fn, time.time() - bg)
def merge_train_by_area():
from io_util import get_block_train_test_split
train_list, test_list = get_block_train_test_split()
random.shuffle(train_list)
f = open('cached/s3dis_merged_train.txt', 'w')
for ai in xrange(1, 7):
cur_data = [[] for _ in xrange(5)]
cur_idx = 0
for fn in train_list:
an = get_area(fn)
if an != ai: continue
data = read_pkl('data/S3DIS/sampled_train_new/' + fn)
for i in xrange(5):
cur_data[i] += data[i]
if len(cur_data[0]) > 1000:
save_pkl(
'data/S3DIS/merged_train_new/{}_{}.pkl'.format(
ai, cur_idx), cur_data)
f.write('data/S3DIS/merged_train_new/{}_{}.pkl\n'.format(
ai, cur_idx))
cur_idx += 1
cur_data = [[] for _ in xrange(5)]
if len(cur_data[0]) > 0:
save_pkl(
'data/S3DIS/merged_train_new/{}_{}.pkl'.format(ai, cur_idx),
cur_data)
f.write('data/S3DIS/merged_train_new/{}_{}.pkl\n'.format(
ai, cur_idx))
cur_idx += 1
print 'area {} done'.format(ai)
f.close()
def semantic3d_test_to_block():
with open('cached/semantic3d_test_stems.txt','r') as f:
lines=f.readlines()
fns=[fn.strip('\n').split(' ')[0] for fn in lines]
pns=[int(fn.strip('\n').split(' ')[1]) for fn in lines]
for fn,pn in zip(fns,pns):
all_data=[[] for _ in xrange(13)]
for t in xrange(pn):
fs=('data/Semantic3D.Net/pkl/test_presample/' + fn + '_{}.pkl'.format(t))
points,labels=read_room_pkl(fs)
xyzs, rgbs, covars, lbls = sample_block(points,labels,ds_stride=sstride,block_size=bsize,
block_stride=bstride,min_pn=min_pn,use_rescale=False,
use_flip=False,use_rotate=False,covar_ds_stride=covar_ds_stride,
covar_nn_size=covar_nn_size,gpu_gather=True)
print 'block num {}'.format(len(xyzs))
data = 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)
for i in xrange(13):
all_data[i]+=data[i]
save_pkl('data/Semantic3D.Net/block/test/'+fn+'.pkl',all_data)
print '{} done'.format(fn)
def merge_train_files():
with open('cached/semantic3d_stems.txt','r') as f:
stems=[line.split(' ')[0] for line in f.readlines()]
with open('cached/semantic3d_train_pkl.txt','r') as f:
fs=[line.strip('\n') for line in f.readlines()]
of=open('cached/semantic3d_merged_train.txt','w')
for s in stems:
idx=0
all_data=[[] for _ in xrange(4)]
for f in fs:
if not f.startswith(s):
continue
data=read_pkl('data/Semantic3D.Net/block/sampled/train/'+f)
for i in xrange(4):
all_data[i]+=data[i]
if len(all_data[0])>300:
print len(all_data[0])
save_pkl('data/Semantic3D.Net/block/sampled/merged/'+s+'_{}.pkl'.format(idx),all_data)
all_data=[[] for _ in xrange(4)]
idx+=1
if len(all_data[0])>0:
save_pkl('data/Semantic3D.Net/block/sampled/merged/'+s+'_{}.pkl'.format(idx),all_data)
idx+=1
of.write('{} {}\n'.format(s,idx))
print '{} done'.format(s)
of.close()
def prepare_s3dis_train_single_file_no_aug(fn):
in_fn = 'data/S3DIS/room_block_10_10/' + fn
bg = time.time()
data = prepare_data(in_fn, False, False, False, False, False, False, 256)
out_fn = 'data/S3DIS/sampled_no_aug/' + fn
save_pkl(out_fn, data)
print 'done {} cost {} s'.format(fn, time.time() - bg)
def split_train_data(split_size):
with open('data/ScanNet/scannet_train.pickle', 'rb') as f:
points = cPickle.load(f)
labels = cPickle.load(f)
cur_size = 0
idx = 0
print 'total size {}'.format(len(points))
while cur_size < len(points):
save_pkl('data/ScanNet/train_split_{}.pkl'.format(idx), [
points[cur_size:cur_size + split_size],
labels[cur_size:cur_size + split_size]
])
idx += 1
cur_size += split_size
print 'cur size {}'.format(cur_size)
def modelnet_dataset_to_block():
from io_util import read_model_h5
train_list=['data/ModelNet40/ply_data_train{}.h5'.format(i) for i in xrange(5)]
test_list=['data/ModelNet40/ply_data_test{}.h5'.format(i) for i in xrange(2)]
# train_list2=['data/ModelNet40/ply_data_train{}.pkl'.format(i) for i in xrange(5)]
# test_list2=['data/ModelNet40/ply_data_test{}.pkl'.format(i) for i in xrange(2)]
for fi,filename in enumerate(train_list[:2]):
points,labels=read_model_h5(filename)
data = normalize_model_hierarchy(points,False)
app_data=[]
app_data.append(labels)
app_data+=data
save_pkl('data/ModelNet40/ply_data_train{}.pkl'.format(fi),app_data)
print len(app_data)
print '{} done'.format(fi)
def semantic3d_presample_block():
with open('cached/semantic3d_test_stems.txt','r') as f:
fns=f.readlines()
fns=[fn.strip('\n').split(' ')[0] for fn in fns]
for fn in fns:
fs=('data/Semantic3D.Net/pkl/test/' + fn + '.pkl')
points,labels=read_room_pkl(fs)
xyzs, rgbs, covars, lbls = sample_block(points,labels,ds_stride=0.03,block_size=50.0,
block_stride=45.0,min_pn=128,use_rescale=False,
use_flip=False,use_rotate=False,covar_ds_stride=0.01,
covar_nn_size=0.1,gpu_gather=True)
for t in xrange(len(xyzs)):
points=np.concatenate([xyzs[t],rgbs[t]],axis=1)
save_pkl('data/Semantic3D.Net/pkl/test_presample/' + fn + '_{}.pkl'.format(t),[points,lbls[t]])
def process():
sess, pls, ops, feed_dict = build_session()
with open('cached/semantic3d_test_stems.txt','r') as f:
lines=f.readlines()
fss=[fn.strip('\n').split(' ')[0] for fn in lines]
for fs in fss[2:3]:
sxyzs,_,sprobs=eval_room_probs(fs,sess, pls, ops, feed_dict)
qxyzs,_=read_pkl('data/Semantic3D.Net/pkl/test/{}.pkl'.format(fs))
qxyzs=np.ascontiguousarray(qxyzs[:,:3],np.float32)
sxyzs=np.ascontiguousarray(sxyzs[:,:3],np.float32)
sprobs=np.ascontiguousarray(sprobs,np.float32)
qprobs=interpolate(sxyzs,sprobs,qxyzs)
save_results(sxyzs,qxyzs,sprobs,qprobs,FLAGS.prefix,fs)
save_pkl('cached/sg28_qxyzs.pkl',qxyzs)
save_pkl('cached/sg28_qprobs.pkl',qprobs)
def process_test_data():
with open('data/ScanNet/scannet_test.pickle', 'rb') as f:
points = cPickle.load(f)
labels = cPickle.load(f)
room_num = len(points)
bg = time.time()
for i in xrange(room_num):
if i % 10 == 0:
print 'idx {} cost {} s'.format(i, time.time() - bg)
bg = time.time()
xyzs, covars, lbls = sample_block_scannet(points[i], labels[i],
ds_stride, block_size,
block_stride, min_pn, False,
False, False, covar_nn_size)
data = normalize_block_scannet(xyzs, covars, lbls, block_size, nr1,
nr2, nr3, vc1, vc2, False, rs_low,
rs_high, pn_limits)
save_pkl('data/ScanNet/sampled_test/test_{}.pkl'.format(i), data)
def process_one_file(fid):
points, labels = read_pkl(
'data/ScanNet/split/train_split_{}.pkl'.format(fid))
room_num = len(points)
all_data = [[] for _ in xrange(12)]
idx = 0
bg = time.time()
for i in xrange(room_num):
if i % 10 == 0:
print 'idx {} cost {} s'.format(i, time.time() - bg)
bg = time.time()
for t in xrange(5):
xyzs, covars, lbls = sample_block_scannet(points[i], labels[i],
ds_stride, block_size,
block_stride, min_pn,
True, True, True,
covar_nn_size)
data = normalize_block_scannet(xyzs, covars, lbls, block_size, nr1,
nr2, nr3, vc1, vc2, True, rs_low,
rs_high, pn_limits)
for s in xrange(len(data)):
all_data[s] += data[s]
if len(all_data[0]) > 300:
save_pkl(
'data/ScanNet/sampled_train/train_{}_{}.pkl'.format(fid, idx),
all_data)
idx += 1
all_data = [[] for _ in xrange(12)]
if len(all_data[0]) > 0:
save_pkl('data/ScanNet/sampled_train/train_{}_{}.pkl'.format(fid, idx),
all_data)
idx += 1
def prepare_subset():
train_list, test_list = get_block_train_test_split()
train_list += test_list
file_list = [fn for fn in train_list if fn.split('_')[-2] == 'office']
for fn in file_list:
bg = time.time()
path = 'data/S3DIS/room_block_10_10/' + fn
flip_x = random.random() < 0.5
flip_y = random.random() < 0.5
swap = random.random() < 0.5
all_data = [[] for _ in xrange(5)]
for i in xrange(1):
data = prepare_subset_single_file(path, 0.075, 1.5, 0.75, 128,
True, swap, flip_x, flip_y, True,
True)
for k in xrange(5):
all_data[k] += data[k]
save_pkl('data/S3DIS/office_block/' + fn, all_data)
print 'done {} cost {} s pn {}'.format(
fn,
time.time() - bg, np.mean([len(xyzs) for xyzs in all_data[0]]))
def prepare_s3dis_test_single_file(fn):
in_fn = 'data/S3DIS/room_block_10_10/' + fn
data = prepare_data(in_fn, False, False, False, False, False, False, 256)
out_fn = 'data/S3DIS/sampled_test_nolimits/' + fn
save_pkl(out_fn, data)
def semantic3d_sample_single_file_training_block(tfs):
fs='data/Semantic3D.Net/block/train/'+tfs
data=semantic3d_process_block_v2(fs)
save_pkl('data/Semantic3D.Net/block/sampled/train/'+tfs,data)
print '{} done'.format(tfs)
