def test_process_context_block():
from draw_util import get_semantic3d_class_colors
lbl_colors=get_semantic3d_class_colors()
fss=read_large_block_list()
random.shuffle(fss)
for fs in fss[:1]:
print fs
# xyzs, rgbs, covars, lbls, ctx_xyzs, ctx_idxs, block_mins = process_context_block(fs)
xyzs, rgbs, covars, lbls, ctx_xyzs, ctx_idxs, block_mins = read_pkl('data/Semantic3D.Net/context/block_avg/'+fs)
for k in xrange(len(xyzs[:10])):
print np.min(lbls[k]),np.max(lbls[k])
ctx_xyzs[k][:,3:6]*=127
ctx_xyzs[k][:,3:6]+=128
rgbs[k]*=127
rgbs[k]+=128
xyzs[k]+=block_mins[k]
ctx_xyzs[k][:,:3]+=block_mins[k]
output_points('test_result/{}xyzs.txt'.format(k),xyzs[k],rgbs[k])
output_points('test_result/{}lbls.txt'.format(k),xyzs[k],lbl_colors[lbls[k]])
output_points('test_result/{}context_xyzs.txt'.format(k),ctx_xyzs[k])
print len(ctx_xyzs[k])
colors=np.random.randint(0,255,[len(ctx_xyzs[k]),3])
output_points('test_result/{}context_xyzs_rcolor.txt'.format(k),ctx_xyzs[k],colors)
output_points('test_result/{}xyzs_rcolor.txt'.format(k),xyzs[k],colors[ctx_idxs[k],:])
cluster_num=5
from sklearn.cluster import KMeans
colors=np.random.randint(0,255,[cluster_num,3])
kmeans=KMeans(cluster_num)
preds=kmeans.fit_predict(covars[k])
output_points('test_result/{}xyzs_cluster.txt'.format(k),xyzs[k],colors[preds])
def test_process_block():
fss = semantic3d_read_train_block_list()
random.shuffle(fss)
colors = get_semantic3d_class_colors()
fss = [
fs for fs in fss
if fs.startswith('untermaederbrunnen_station1_xyz_intensity_rgb')
]
orientations = [[] for _ in xrange(6)]
for t in xrange(6):
for fs in fss:
if fs.split('_')[-1].startswith(str(t)):
orientations[t].append(fs)
for i in xrange(1):
for t, fs in enumerate(orientations[i]):
xyzs, rgbs, covars, lbls, block_mins = read_pkl(
'data/Semantic3D.Net/block/sampled/' + fs)
for k in xrange(len(xyzs)):
# idxs=libPointUtil.gridDownsampleGPU(xyzs[k],0.2,False)
pts = xyzs[k] #[idxs]
lbl = lbls[k] #[idxs]
rgb = rgbs[k] #[idxs]
print np.min(pts,
axis=0), np.max(pts, axis=0) - np.min(pts, axis=0)
output_points('test_result/colors{}_{}_{}.txt'.format(i, t, k),
pts + block_mins[k], rgb * 127 + 128)
output_points('test_result/labels{}_{}_{}.txt'.format(i, t, k),
pts + block_mins[k], colors[lbl, :])
def save_results(sxyzs, qxyzs, sprobs, qprobs, prefix, fs):
colors = get_semantic3d_class_colors()
spreds = np.argmax(sprobs[:, 1:], axis=1) + 1
qpreds = np.argmax(qprobs[:, 1:], axis=1) + 1
dir = 'data/Semantic3D.Net/{}'.format(prefix)
if not os.path.exists(dir): os.mkdir(dir)
with open('{}/{}.labels'.format(dir, fs), 'w') as f:
for pred in qpreds:
f.write('{}\n'.format(pred))
idxs = libPointUtil.gridDownsampleGPU(sxyzs, 0.3, False)
sxyzs = sxyzs[idxs]
spreds = spreds[idxs]
output_points('{}/{}_sparse.txt'.format(dir, fs), sxyzs, colors[spreds])
idxs = libPointUtil.gridDownsampleGPU(qxyzs, 0.3, False)
qxyzs = qxyzs[idxs]
qpreds = qpreds[idxs]
output_points('{}/{}_dense.txt'.format(dir, fs), qxyzs, colors[qpreds])
def test_big_block():
fss = semantic3d_read_train_block_list()
random.shuffle(fss)
colors = get_semantic3d_class_colors()
fss = [
fs for fs in fss
if fs.startswith('untermaederbrunnen_station1_xyz_intensity_rgb')
]
orientations = [[] for _ in xrange(6)]
for t in xrange(6):
for fs in fss:
if fs.split('_')[-1].startswith(str(t)):
orientations[t].append(fs)
for i in xrange(6):
for t, fs in enumerate(orientations[i]):
points, labels = read_pkl('data/Semantic3D.Net/block/train/' + fs)
idxs = libPointUtil.gridDownsampleGPU(points, 0.2, False)
points = points[idxs]
labels = labels[idxs]
print points.shape
output_points('test_result/{}_{}_colors.txt'.format(i, t), points)
output_points('test_result/{}_{}_labels.txt'.format(i, t), points,
colors[labels, :])
qrn = qn / rn
if qn % rn != 0: qrn += 1
print 'qrn {} sxyzs num {}'.format(qrn, sxyzs.shape[0])
qprobs = []
for t in xrange(qrn):
beg_idxs = t * rn
end_idxs = min((t + 1) * rn, qn)
qrprobs = interpolate(sxyzs, sprobs, qxyzs[beg_idxs:end_idxs])
print 'interpolate {} done'.format(t)
qprobs.append(qrprobs)
qprobs = np.concatenate(qprobs, axis=0)
qpreds = np.argmax(qprobs[:, 1:], axis=1) + 1
colors = get_semantic3d_class_colors()
spreds = np.argmax(sprobs[:, 1:], axis=1) + 1
print 'total cost {} s'.format(time.time() - begin)
with open('data/Semantic3D.Net/{}.labels'.format(fn), 'w') as f:
for p in qpreds:
f.write('{}\n'.format(p))
idxs = libPointUtil.gridDownsampleGPU(sxyzs, 0.1, False)
sxyzs = sxyzs[idxs]
spreds = spreds[idxs]
output_points('test_result/{}_sparse.txt'.format(fn), sxyzs,
colors[spreds, :])
idxs = libPointUtil.gridDownsampleGPU(qxyzs, 0.1, False)
qxyzs = qxyzs[idxs]