def test_neighborhood():
# pt_num=np.random.randint(20000,50000)
pt_num=10240
pts=np.random.uniform(0,1,[pt_num,3])
pts=np.asarray(pts,dtype=np.float32)
idxs=np.random.choice(pt_num,100,False)
idxs=np.asarray(idxs,np.int32)
for i in xrange(10000):
nidxs=libPointUtil.findNeighborRadiusGPU(pts,idxs,0.1,30)
def point2ndixs(pts, radius):
leafsize = 10 if pts.shape[0] > 100 else 1
if pts.shape[0] > 8000:
nidxs = libPointUtil.findNeighborRadiusGPU(pts, radius, leafsize)
else:
nidxs = libPointUtil.findNeighborRadiusCPU(pts, radius, leafsize)
nidxs_lens = [len(nidx) for nidx in nidxs]
nidxs_lens = np.asarray(nidxs_lens, dtype=np.int32)
nidxs = np.concatenate(nidxs, axis=0)
nidxs_bgs = compute_nidxs_bgs(nidxs_lens)
cindxs = compute_cidxs(nidxs_lens)
return nidxs, nidxs_lens, nidxs_bgs, cindxs
def test_concat_non_center():
import libPointUtil
pts=np.random.uniform(-1.0,1.0,[20,3])
pts=np.asarray(pts,dtype=np.float32)
nidxs=libPointUtil.findNeighborRadiusGPU(pts,1.0)
nidxs_lens=np.asarray([len(idxs) for idxs in nidxs],dtype=np.int32)
nidxs_bgs=compute_nidxs_bgs(nidxs_lens)
nidxs=np.concatenate(nidxs,axis=0)
nidxs=np.asarray(nidxs,dtype=np.int32)
pts=np.asarray(pts,np.float64)
ofeats=np_concat_non_center_forward(pts,nidxs,nidxs_lens,nidxs_bgs)
dofeats=np.random.uniform(-1,1,ofeats.shape)
difeats=np_concat_non_center_backward(dofeats,nidxs,nidxs_lens,nidxs_bgs)
f=lambda ifeats: np_concat_non_center_forward(ifeats,nidxs,nidxs_lens,nidxs_bgs)
difeats_num=eval_numerical_gradient_array(f,pts,dofeats)
print pts
print ofeats
print 'diff {} '.format(np.max(difeats-difeats_num))
def tesst_concat_non_center_scatter():
pts = np.random.uniform(-1.0, 1.0, [20, 3])
pts = np.asarray(pts, dtype=np.float32)
nidxs = libPointUtil.findNeighborRadiusGPU(pts, 1.0)
nidxs_lens = np.asarray([len(idxs) for idxs in nidxs], dtype=np.int32)
nidxs_bgs = compute_nidxs_bgs(nidxs_lens)
nidxs = np.concatenate(nidxs, axis=0)
nidxs = np.asarray(nidxs, dtype=np.int32)
pts = np.asarray(pts, np.float64)
ofeats = np_concat_non_center_forward(pts, nidxs, nidxs_lens, nidxs_bgs)
dofeats = np.random.uniform(-1, 1, ofeats.shape)
difeats = np_concat_non_center_backward(dofeats, nidxs, nidxs_lens,
nidxs_bgs)
ifeats = np.ascontiguousarray(pts, np.float32)
dofeats = np.ascontiguousarray(dofeats, np.float32)
ofeats_tf, difeats_tf = eval_concat_non_center_forward(
ifeats, nidxs, nidxs_lens, nidxs_bgs, dofeats)
print 'forward diff {}'.format(np.max(ofeats_tf - ofeats))
print 'backward diff {}'.format(np.max(np.abs(difeats_tf - difeats)))
print np.mean(difeats_tf)
def test_covars():
pts, _ = read_room_h5('data/S3DIS/room/16_Area_1_office_15.h5')
ds_idxs, _ = libPointUtil.gridDownsampleGPU(pts, 0.05, True)
pts = pts[ds_idxs, :]
spts = np.ascontiguousarray(pts[:, :3])
nidxs = libPointUtil.findNeighborRadiusGPU(spts, 0.2)
nidxs_lens = np.asarray([len(idxs) for idxs in nidxs], dtype=np.int32)
nidxs_bgs = compute_nidxs_bgs(nidxs_lens)
nidxs = np.concatenate(nidxs, axis=0)
begin = time.time()
for i in xrange(10000):
covars = libPointUtil.computeCovarsGPU(spts, nidxs, nidxs_lens,
nidxs_bgs)
print 'cost {} s'.format(time.time() - begin)
from sklearn.cluster import KMeans
kmeans = KMeans(5)
preds = kmeans.fit_predict(covars)
colors = np.random.randint(0, 255, [5, 3])
output_points('test_result/cluster.txt', pts, colors[preds, :])
def sample_block_scannet(points,
labels,
ds_stride,
block_size,
block_stride,
min_pn,
use_rescale=False,
use_flip=False,
use_rotate=False,
covar_nn_size=0.1):
xyzs = np.ascontiguousarray(points[:, :3])
min_xyzs = np.min(xyzs, axis=0, keepdims=True)
max_xyzs = np.max(xyzs, axis=0, keepdims=True)
# flip
if use_flip:
if random.random() < 0.5:
xyzs = swap_xy(xyzs)
min_xyzs = swap_xy(min_xyzs)
max_xyzs = swap_xy(max_xyzs)
if random.random() < 0.5:
xyzs = flip(xyzs, axis=0)
min_xyzs[:, 0], max_xyzs[:, 0] = -max_xyzs[:, 0], -min_xyzs[:, 0]
if random.random() < 0.5:
xyzs = flip(xyzs, axis=1)
min_xyzs[:, 1], max_xyzs[:, 1] = -max_xyzs[:, 1], -min_xyzs[:, 1]
# rescale
if use_rescale:
rescale = np.random.uniform(0.9, 1.1, [1, 3])
xyzs[:, :3] *= rescale
min_xyzs *= rescale
max_xyzs *= rescale
# rotate
if use_rotate:
if random.random() > 0.3:
angle = random.random() * np.pi / 2.0
xyzs = rotate(xyzs, angle)
min_xyzs = np.min(xyzs, axis=0, keepdims=True)
max_xyzs = np.max(xyzs, axis=0, keepdims=True)
ds_idxs = libPointUtil.gridDownsampleGPU(xyzs, ds_stride, False)
covar_nidxs = libPointUtil.findNeighborRadiusGPU(xyzs, ds_idxs,
covar_nn_size)
covar_nidxs_lens = np.ascontiguousarray(
[len(idxs) for idxs in covar_nidxs], np.int32)
covar_nidxs_bgs = compute_nidxs_bgs(covar_nidxs_lens)
covar_nidxs = np.ascontiguousarray(np.concatenate(covar_nidxs, axis=0),
dtype=np.int32)
covars = libPointUtil.computeCovarsGPU(xyzs, covar_nidxs, covar_nidxs_lens,
covar_nidxs_bgs)
xyzs = xyzs[ds_idxs, :]
lbls = labels[ds_idxs]
xyzs -= min_xyzs
idxs = uniform_sample_block(xyzs,
block_size,
block_stride,
normalized=True,
min_pn=min_pn)
xyzs += min_xyzs
xyzs, covars, lbls = fetch_subset([xyzs, covars, lbls], idxs)
return xyzs, covars, lbls
return vals
if __name__ == "__main__":
pts,_=read_room_h5('data/S3DIS/room/16_Area_1_office_15.h5')
ds_idxs,_=libPointUtil.gridDownsampleGPU(pts,0.05,True)
pts=pts[ds_idxs,:]
block_idxs=libPointUtil.sampleRotatedBlockGPU(pts,1.5,3.0,0.0)
block_idxs=[idxs for idxs in block_idxs if len(idxs)>2048]
print 'mean block pt_num: {}'.format(np.mean(np.asarray([len(idxs) for idxs in block_idxs])))
bid=np.random.randint(0,len(block_idxs))
pts=pts[block_idxs[bid],:]
spts=np.ascontiguousarray(pts[:,:3])
nidxs=libPointUtil.findNeighborRadiusGPU(spts,0.08)
nidxs_lens=np.asarray([len(idxs) for idxs in nidxs],dtype=np.int32)
nidxs_bgs=compute_nidxs_bgs(nidxs_lens)
cidxs=compute_cidxs(nidxs_lens)
nidxs=np.concatenate(nidxs,axis=0)
print 'pn*n: {}'.format(nidxs.shape)
print 'pn: {}'.format(nidxs_bgs.shape)
print 'avg n: {}'.format(float(nidxs.shape[0])/nidxs_bgs.shape[0])
pmiu=neighbor_anchors()
pmiu=pmiu.transpose()
print 'pmiu {}'.format(pmiu.shape)
dpfeats=np.random.uniform(-1.0,1.0,[pts.shape[0],final_dims])
dpfeats=np.asarray(dpfeats,dtype=np.float32)
vals=eval_conv_xyz_feats(pts[:,:3],pts[:,3:],nidxs,nidxs_lens,nidxs_bgs,pmiu,dpfeats,cidxs)