def flow_embedding_module(xyz1, xyz2, feat1, feat2, radius, nsample, mlp, is_training, bn_decay, scope, bn=True, pooling='max', knn=True, corr_func='elementwise_product'):
"""
Input:
xyz1: (batch_size, npoint, 3)
xyz2: (batch_size, npoint, 3)
feat1: (batch_size, npoint, channel)
feat2: (batch_size, npoint, channel)
Output:
xyz1: (batch_size, npoint, 3)
feat1_new: (batch_size, npoint, mlp[-1])
"""
if knn:
_, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, cnt = query_ball_point(radius, nsample, xyz2, xyz1)
_, idx_knn = knn_point(nsample, xyz2, xyz1)
cnt = tf.tile(tf.expand_dims(cnt, -1), [1,1,nsample])
idx = tf.where(cnt > (nsample-1), idx, idx_knn)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint, nsample, channel
feat1_expanded = tf.expand_dims(feat1, 2) # batch_size, npoint, 1, channel
# TODO: change distance function
if corr_func == 'elementwise_product':
feat_diff = feat2_grouped * feat1_expanded # batch_size, npoint, nsample, channel
elif corr_func == 'concat':
feat_diff = tf.concat(axis=-1, values=[feat2_grouped, tf.tile(feat1_expanded,[1,1,nsample,1])]) # batch_size, npoint, sample, channel*2
elif corr_func == 'dot_product':
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'cosine_dist':
feat2_grouped = tf.nn.l2_normalize(feat2_grouped, -1)
feat1_expanded = tf.nn.l2_normalize(feat1_expanded, -1)
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
elif corr_func == 'flownet_like': # assuming square patch size k = 0 as the FlowNet paper
batch_size = xyz1.get_shape()[0].value
npoint = xyz1.get_shape()[1].value
feat_diff = tf.reduce_sum(feat2_grouped * feat1_expanded, axis=[-1], keep_dims=True) # batch_size, npoint, nsample, 1
total_diff = tf.concat(axis=-1, values=[xyz_diff, feat_diff]) # batch_size, npoint, nsample, 4
feat1_new = tf.reshape(total_diff, [batch_size, npoint, -1]) # batch_size, npoint, nsample*4
#feat1_new = tf.concat(axis=[-1], values=[feat1_new, feat1]) # batch_size, npoint, nsample*4+channel
return xyz1, feat1_new
feat1_new = tf.concat([feat_diff, xyz_diff], axis=3) # batch_size, npoint, nsample, [channel or 1] + 3
# TODO: move scope to outer indent
with tf.variable_scope(scope) as sc:
for i, num_out_channel in enumerate(mlp):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv_diff_%d'%(i), bn_decay=bn_decay)
if pooling=='max':
feat1_new = tf.reduce_max(feat1_new, axis=[2], keep_dims=False, name='maxpool_diff')
elif pooling=='avg':
feat1_new = tf.reduce_mean(feat1_new, axis=[2], keep_dims=False, name='avgpool_diff')
return xyz1, feat1_new
def test(self):
knn = True
np.random.seed(100)
pts = np.random.random((32, 512, 64)).astype("float32")
tmp1 = np.random.random((32, 512, 3)).astype("float32")
tmp2 = np.random.random((32, 128, 3)).astype("float32")
with tf.device("/gpu:0"):
points = tf.constant(pts)
xyz1 = tf.constant(tmp1)
xyz2 = tf.constant(tmp2)
radius = 0.1
nsample = 64
if knn:
_, idx = knn_point(nsample, xyz1, xyz2)
grouped_points = group_point(points, idx)
else:
idx, _ = query_ball_point(radius, nsample, xyz1, xyz2)
grouped_points = group_point(points, idx)
# grouped_points_grad = tf.ones_like(grouped_points)
# points_grad = tf.gradients(grouped_points, points, grouped_points_grad)
with tf.compat.v1.Session("") as sess:
now = time.time()
for _ in range(100):
ret = sess.run(grouped_points)
print(time.time() - now)
print(ret.shape, ret.dtype)
print(ret)
def get_uniform_loss(pcd,
percentages=[0.004, 0.006, 0.008, 0.010, 0.012],
radius=1.0):
B, N, C = pcd.get_shape().as_list()
npoint = int(N * 0.05)
loss = []
for p in percentages:
nsample = int(N * p)
r = math.sqrt(p * radius)
disk_area = math.pi * (radius**2) * p / nsample
#print(npoint,nsample)
new_xyz = gather_point(pcd, farthest_point_sample(
npoint, pcd)) # (batch_size, npoint, 3)
idx, pts_cnt = query_ball_point(
r, nsample, pcd, new_xyz) #(batch_size, npoint, nsample)
#expect_len = tf.sqrt(2*disk_area/1.732)#using hexagon
expect_len = tf.sqrt(disk_area) # using square
grouped_pcd = group_point(pcd, idx)
grouped_pcd = tf.concat(tf.unstack(grouped_pcd, axis=1), axis=0)
var, _ = knn_point(2, grouped_pcd, grouped_pcd)
uniform_dis = -var[:, :, 1:]
uniform_dis = tf.sqrt(tf.abs(uniform_dis + 1e-8))
uniform_dis = tf.reduce_mean(uniform_dis, axis=[-1])
uniform_dis = tf.square(uniform_dis - expect_len) / (expect_len + 1e-8)
uniform_dis = tf.reshape(uniform_dis, [-1])
mean, variance = tf.nn.moments(uniform_dis, axes=0)
mean = mean * math.pow(p * 100, 2)
#nothing 4
loss.append(mean)
return tf.add_n(loss) / len(percentages)
def get_model(sample_num, sample_scale, point_cloud, is_training, filter_sizes, filter_num, bn_decay=None):
'''
Input:
sample_num: int32; sample M points from originally N points.
sample_scale: []; find Ki points from sampled points' neighbours
'''
batch_size = point_cloud.get_shape()[0].value
feature_collection = []
channels = [32, 64, 128]
M_sampled_points = farthest_point_sample(sample_num, point_cloud)
# [batch, sample_num, 3]
new_xyz = gather_point(point_cloud, M_sampled_points)
for i, scale in enumerate(sample_scale):
# [batch, sample_num, scale]
_, idx = knn_point(scale, point_cloud, new_xyz)
# [batch, sample_num, scale, 3]
points_features = group_point(point_cloud, idx)
for j, channel in enumerate(channels):
# [batch, sample_num, scale, channel]
points_features = tf_util.conv2d(points_features, channel, [1, 1],
padding = 'VALID', stride = [1, 1],
bn = True, is_training = is_training,
scope='conv_%d_%d'%(i, j), bn_decay = bn_decay,
data_format = 'NHWC')
# [batch, sample_num, 1, 128]
points_features = tf.reduce_max(points_features, axis = [2], keep_dims = True, name = 'maxpool')
# [batch, sample_num, 128]
points_features = tf.squeeze(points_features, [2])
# [batch, sample_num, 1, 128]
points_features = tf.expand_dims(points_features, 2)
# [batch * sample_num, 1, 128]
points_features = tf.reshape(points_features, [batch_size * sample_num, 1, channels[-1]])
feature_collection.append(points_features)
# [batch * sample_num, len(sample_scale), 128]
textcnn_embedding = tf.concat(feature_collection, 1)
# [batch * sample_num, feature_size = 128]
textcnn_encoded = get_textcnn_model(textcnn_embedding, filter_sizes, filter_num, is_training, bn_decay)
# [batch, sample_num, feature_size]
textcnn_encoded = tf.reshape(textcnn_encoded, [batch_size, sample_num, -1])
# [batch, sample_num, 1, feature_size]
global_feature = tf.expand_dims(textcnn_encoded, 2)
channels = [256, 512, 1024]
for i, channel in enumerate(channels):
# [batch, sample_num, 1, channel]
global_feature = tf_util.conv2d(global_feature, channel, [1, 1],
padding = 'VALID', stride = [1, 1],
bn = True, is_training = is_training,
scope='feature_aggregation_conv_%d'%(i), bn_decay = bn_decay,
data_format = 'NHWC')
# [batch, 1, 1, 1024]
global_feature = tf.reduce_max(global_feature, axis = [1], keep_dims = True, name = 'global_feature_maxpool')
# [batch, 1024]
global_feature = tf.reshape(global_feature, [batch_size, -1])
classify_feature = tf_util.fully_connected(global_feature, 512, bn=True, is_training=is_training, scope='fc1', bn_decay=bn_decay)
classify_feature = tf_util.dropout(classify_feature, keep_prob=0.4, is_training=is_training, scope='dp1')
classify_feature = tf_util.fully_connected(classify_feature, 256, bn=True, is_training=is_training, scope='fc2', bn_decay=bn_decay)
classify_feature = tf_util.dropout(classify_feature, keep_prob=0.4, is_training=is_training, scope='dp2')
classify_feature = tf_util.fully_connected(classify_feature, 40, activation_fn=None, scope='fc3')
return classify_feature
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
''' New sample_and_group with Fully Delayed-Aggregation
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
point_cloud_shape = points.get_shape()
batch_size = point_cloud_shape[0].value
num_points = point_cloud_shape[1].value
num_dims = point_cloud_shape[-1].value
# get the index and coordinates of sampled points
sampled_idx = tf.random_uniform(shape=(batch_size, npoint),maxval=npoint-1,dtype=tf.int32)
new_xyz = gather_point(xyz, sampled_idx) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
# grouping:
idx_ = tf.range(batch_size) * num_points
idx_ = tf.reshape(idx_, [batch_size, 1, 1])
points = tf.reshape(points, [-1, num_dims])
new_points = tf.gather(points, idx + idx_)
# get the sampled points as centroids with xyz+feature for coord correction
sampled_idx = tf.expand_dims(sampled_idx, -1)
sampled_points = tf.gather(points, sampled_idx + idx_)
# coord correction
new_points -= sampled_points
# get the new xyz set for sampled points and neighbors
xyz_shape = xyz.get_shape()
batch_size = xyz_shape[0].value
num_points = xyz_shape[1].value
num_dims = xyz_shape[-1].value
idx_ = tf.range(batch_size) * num_points
idx_ = tf.reshape(idx_, [batch_size, 1, 1])
xyz_reshaped = tf.reshape(xyz, [-1, num_dims])
grouped_xyz = tf.gather(xyz_reshaped, idx + idx_)
grouped_xyz -= tf.expand_dims(new_xyz, 2) # translation normalization
return new_xyz, new_points, idx, grouped_xyz
def pc_sampling(xyz, feat, nsample, num_point, scope='sampling'):
""" Fully connected layer with non-linear operation.
Args:
xyz: 3-D tensor B x N x 3
nsample: k
num_point: N2
feat: 3-D tensor B x N x C
Returns:
feat_sample: 3-D tensor B x N2 x C
"""
with tf.variable_scope(scope) as sc:
xyz_new = gather_point(xyz, farthest_point_sample(num_point, xyz))
_, idx_pooling = knn_point(nsample, xyz, xyz_new)
grouped_points = group_point(feat, idx_pooling)
feat_sample = tf.nn.max_pool(grouped_points, [1, 1, nsample, 1],
[1, 1, 1, 1],
padding='VALID',
data_format='NHWC',
name="MAX_POOLING")
feat_sample = tf.squeeze(feat_sample, axis=[2])
return feat_sample, xyz_new
def sample_and_group_ByKeypoints(keypoints_xyz, nsample, xyz, sn, is_training):
'''
Input:
keypoints_xyz:BxMx3
nsample: int32
xyz: bxNx3
Return:
grouped_augmented:BxMxnsamplex3
idx:BxMxnsample int
grouped_xyz:#BxMxnsamplex3
grouped_xyz_center:BxMx3
'''
_, idx = knn_point(nsample, xyz, keypoints_xyz)
grouped_xyz = group_point(xyz, idx) #BxMxnsamplex3
grouped_xyz_center = tf.reduce_mean(grouped_xyz, axis=2) #BxMx3
grouped_xyz_decentered = grouped_xyz - tf.tile(
tf.expand_dims(grouped_xyz_center, 2), [1, 1, nsample, 1])
if sn is not None:
grouped_sn = group_point(sn, idx) #BxMxnsamplex3
grouped_augmented = tf.concat([grouped_xyz_decentered, grouped_sn],
-1) #BxMxnsamplex6
else:
grouped_augmented = grouped_xyz_decentered #BxMxnsamplex3
return grouped_augmented, idx, grouped_xyz, grouped_xyz_center
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group_layer1(npoint,
radius,
nsample,
xyz,
points,
knn=False,
use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
#tf_ops/samples/tf_sampling.py
new_xyz = gather_point(xyz, farthest_point_sample(
npoint, xyz)) # (batch_size, npoint, 3),挑选满足条件的512个像素
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz,
new_xyz) # 提取512个点index每个点分别属于32个簇之一
grouped_xyz = group_point(
xyz, idx) # (batch_size, npoint, nsample, 3) #提取512个像素每个像素分别属于32个簇之一
grouped_xyz -= tf.tile(
tf.expand_dims(new_xyz, 2), [1, 1, nsample, 1]
) # translation normalization 首先增加1维,(bs,512,3)->(bs,512,1,3),第三维张量扩充32倍->(bs,512,32,3),这里假定npoints=512，nsamples=32
kernel = tf.Variable(tf.random_normal([32, 16, 3], stddev=0.1, seed=1),
name='kernel')
tf.add_to_collection("kernel", kernel)
# kernel = tf.convert_to_tensor(kernel)
kc_points = kernel_correlation(
grouped_xyz, kernel,
0.005) # KC module ==>(b,l,n)===>(BS, npoint, 1, l)
kc_points = tf.transpose(kc_points, perm=[0, 2, 1])
kc_points = tf.tile(tf.expand_dims(kc_points, 2), [1, 1, nsample, 1])
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz: #是否考虑原始xyz空间信息
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nsample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
new_points = tf.concat([kc_points, new_points], axis=-1)
return new_xyz, new_points, idx, grouped_xyz
def set_upconv_module(xyz1, xyz2, feat1, feat2, nsample, mlp, mlp2, is_training,
scope, bn_decay=None, bn=True, pooling='max', radius=None,
knn=True):
"""
Feature propagation from xyz2 (less points) to xyz1 (more points)
Inputs:
xyz1: (batch_size, npoint1, 3)
xyz2: (batch_size, npoint2, 3)
feat1: (batch_size, npoint1, channel1) features for xyz1 points (earlier layers)
feat2: (batch_size, npoint2, channel2) features for xyz2 points
Output:
feat1_new: (batch_size, npoint2, mlp[-1] or mlp2[-1] or channel1+3)
TODO: Add support for skip links. Study how delta(XYZ) plays a role in feature updating.
"""
with tf.variable_scope(scope) as sc:
if knn:
l2_dist, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz2, xyz1)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint1, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint1, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint1, nsample, 3
feat2_grouped = group_point(feat2,
idx) # batch_size, npoint1, nsample, channel2
net = tf.concat([feat2_grouped, xyz_diff],
axis=3) # batch_size, npoint1, nsample, channel2+3
if mlp is None: mlp = []
for i, num_out_channel in enumerate(mlp):
net = tf_util.conv2d(net, num_out_channel, [1, 1],
padding='VALID', stride=[1, 1],
bn=True, is_training=is_training,
scope='conv%d' % (i), bn_decay=bn_decay)
if pooling == 'max':
feat1_new = tf.reduce_max(net, axis=[2], keep_dims=False,
name='maxpool') # batch_size, npoint1, mlp[-1]
elif pooling == 'avg':
feat1_new = tf.reduce_mean(net, axis=[2], keep_dims=False,
name='avgpool') # batch_size, npoint1, mlp[-1]
if feat1 is not None:
feat1_new = tf.concat([feat1_new, feat1],
axis=2) # batch_size, npoint1, mlp[-1]+channel1
feat1_new = tf.expand_dims(feat1_new,
2) # batch_size, npoint1, 1, mlp[-1]+channel2
if mlp2 is None: mlp2 = []
for i, num_out_channel in enumerate(mlp2):
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1, 1],
padding='VALID', stride=[1, 1],
bn=True, is_training=is_training,
scope='post-conv%d' % (i),
bn_decay=bn_decay)
feat1_new = tf.squeeze(feat1_new, [2]) # batch_size, npoint1, mlp2[-1]
return feat1_new
def sample_and_group(npoint,
radius,
nsample,
xyz,
points,
tnet_spec=None,
knn=False,
use_xyz=True,
centralize_points=False):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
fpsidx = farthest_point_sample(npoint, xyz)
new_xyz = gather_point(xyz, fpsidx) # (batch_size, npoint, 3)
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2),
[1, 1, nsample, 1]) # translation normalization
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if centralize_points:
central_points = gather_point(points[:, :, :3], fpsidx)
grouped_points = tf.concat((grouped_points[:, :, :, :3] - tf.tile(
tf.expand_dims(central_points, 2), [1, 1, nsample, 1]),
grouped_points[:, :, :, 3:]), -1)
if use_xyz:
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nsample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def get_uniform_loss_knn(pred):
var, _ = knn_point(6, pred, pred)
mean = tf.reduce_mean(var, axis=2)
_, variance = tf.nn.moments(mean, axes=[1])
variance1 = tf.reduce_sum(variance)
_, var = tf.nn.moments(var, axes=[2])
var = tf.reduce_sum(var)
variance2 = tf.reduce_sum(var)
return variance1 + variance2
def sample_and_group(npoint,
radius,
nsample,
xyz,
points,
tnet_spec=None,
knn=False,
use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
Workflow:
Find the <npoint> down-sampled farest points by <farthest_point_sample>
For each down-sampled point, find <nsample> sub-group points by <query_ball_point>
'''
new_xyz = gather_point(
xyz, farthest_point_sample(npoint, xyz)
) # (batch_size, npoint, 3) the points sampled with farest distance
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
# [batch_size,npoint,nsample] [batch_size,npoint]
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(
new_xyz, 2), [1, 1, nsample, 1
]) # translation normalization: minus the center point
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def pointnet_sa_module_msg(xyz, points, npoint, radius_list, nsample_list, mlp_list, is_training, bn_decay, scope, bn=True, knn=True, use_xyz=True, use_nchw=False, rearrange=False):
''' PointNet Set Abstraction (SA) module with Multi-Scale Grouping (MSG)
Input:
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor
npoint: int32 -- #points sampled in farthest point sampling
radius: list of float32 -- search radius in local region
nsample: list of int32 -- how many points in each local region
mlp: list of list of int32 -- output size for MLP on each point
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
use_nchw: bool, if True, use NCHW data format for conv2d, which is usually faster than NHWC format
Return:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, \sum_k{mlp[k][-1]}) TF tensor
'''
batch_size = xyz.get_shape()[0].value
data_format = 'NCHW' if use_nchw else 'NHWC'
with tf.variable_scope(scope) as sc:
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz))
new_points_list = []
for i in range(len(nsample_list)):
radius = radius_list[i]
nsample = nsample_list[i]
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, _ = query_ball_point(radius, nsample, xyz, new_xyz)
#idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1])
if points is not None:
grouped_points = group_point(points, idx)
if use_xyz:
grouped_points = tf.concat([grouped_points, grouped_xyz], axis=-1)
else:
grouped_points = grouped_xyz
if use_nchw: grouped_points = tf.transpose(grouped_points, [0,3,1,2])
for j,num_out_channel in enumerate(mlp_list[i]):
grouped_points = tf_util.conv2d(grouped_points, num_out_channel, [1,1],
padding='VALID', stride=[1,1], bn=bn, is_training=is_training,
scope='conv%d_%d'%(i,j), bn_decay=bn_decay, data_format=data_format)
if use_nchw: grouped_points = tf.transpose(grouped_points, [0,2,3,1])
new_points = tf.reduce_max(grouped_points, axis=[2])
if rearrange:
new_points = tf.expand_dims(new_points, -1)
new_points_list.append(new_points)
new_points_concat = tf.concat(new_points_list, axis=-1)
new_points_concat = tf.reshape(new_points_concat, [batch_size, npoint, -1])
return new_xyz, new_points_concat
def sample_and_group(npoint,
radius,
nsample,
xyz,
points,
knn=False,
use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
sampled_idx: () TF tensor, idx for sampled points
'''
point_cloud_shape = points.get_shape()
batch_size = point_cloud_shape[0].value
sampled_idx = farthest_point_sample(npoint, xyz)
# sampled_idx = tf.random_uniform(shape=(batch_size,npoint),maxval=npoint-1,dtype=tf.int32)
new_xyz = gather_point(xyz, sampled_idx) # (batch_size, npoint, 3)
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.expand_dims(new_xyz, 2) # translation normalization
if points is not None:
# grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
# print("grouped_points:", grouped_points.shape)
# grouping:
grouped_points = new_group_point(
points, idx) # (batch_size, npoint, nsample, channel)
print("grouped_points:", grouped_points.shape)
new_points = grouped_points
else:
new_points = grouped_xyz
print("[Group] points:", new_points.shape)
return new_xyz, new_points, idx, grouped_xyz
def get_interpolated_rgb(xyz, point_cloud):
_, idx = knn_point(3, point_cloud[:, :, :3], xyz)
grouped_xyz_rgb = group_point(point_cloud, idx) # (batch size, 2048, 3, 6)
dist = ((tf.expand_dims(xyz, 2) - grouped_xyz_rgb[:, :, :, :3])**2)
dist = tf.maximum(dist, 1e-10)
norm = tf.reduce_sum((1/dist), axis=2) # (batch, 2048, 3)
weighted_rgb = (1/dist)*grouped_xyz_rgb[:, :, :, 3:]
weighted_norm_rgb = tf.reduce_sum(weighted_rgb, 2)/norm
return weighted_norm_rgb, dist, grouped_xyz_rgb
def sample_and_group(npoint,
radius,
nsample,
xyz,
points,
knn=False,
use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
#tf_ops/samples/tf_sampling.py
new_xyz = gather_point(xyz, farthest_point_sample(
npoint, xyz)) # (batch_size, npoint, 3),挑选满足条件的512个像素
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz,
new_xyz) # 提取512个点index每个点分别属于32个簇之一
grouped_xyz = group_point(
xyz, idx) # (batch_size, npoint, nsample, 3) #提取512个像素每个像素分别属于32个簇之一
grouped_xyz -= tf.tile(
tf.expand_dims(new_xyz, 2), [1, 1, nsample, 1]
) # translation normalization 首先增加1维,(bs,512,3)->(bs,512,1,3),第三维张量扩充32倍->(bs,512,32,3),这里假定npoints=512，nsamples=32
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz: #是否考虑原始xyz空间信息
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nsample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec=None, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
if np.isscalar(radius):
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
else:
idx_list = []
for radius_one, xyz_one, new_xyz_one in zip(tf.unstack(radius,axis=0), tf.unstack(xyz, axis=0),tf.unstack(new_xyz, axis=0)):
idx_one, _ = query_ball_point(radius_one, nsample, tf.expand_dims(xyz_one, axis=0), tf.expand_dims(new_xyz_one, axis=0))
idx_list.append(idx_one)
idx = tf.stack(idx_list, axis=0)
idx = tf.squeeze(idx, axis=1)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
# new_points = tf.concat([grouped_xyz, tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]),grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
new_points = tf.concat([grouped_xyz, grouped_points],axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
# new_points = tf.concat([grouped_xyz, tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1])], axis=-1)
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group(npoint, radius, nsample, xyz, points, knn=False,
use_xyz=True):
'''
Input:
npoint: int32 = 1024
radius: float32 = 0.5,1,2,4
nsample: int32 = 16
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(npoint,
xyz)) ### Sampling using farthest point sampling
# import ipdb; ipdb.set_trace()
print ('check for seg fault')
# xyz.shape
# TensorShape([Dimension(4), Dimension(2048), Dimension(3)])
# new_xyz.shape
# TensorShape([Dimension(4), Dimension(1024), Dimension(3)])
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz,
new_xyz) ### Grouping using ball query
grouped_xyz = group_point(xyz,
idx) # (batch_size, npoint, nsample, 3) ### Resulting grouped coordinates
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2),
[1, 1, nsample, 1]) ### translation normalization
if points is not None:
grouped_points = group_point(points,
idx) # (batch_size, npoint, nsample, channel) ### Resulting grouped features
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def softmax_embedding(xyz1, xyz2, feat1, feat2,
radius, nsample,
mlp,
is_training, bn_decay, scope,
bn=True, knn=True, corr_func='concat'):
if knn:
_, idx = knn_point(nsample, xyz2, xyz1)
else:
idx, _ = query_ball_point(radius, nsample, xyz2, xyz1)
xyz2_grouped = group_point(xyz2, idx) # batch_size, npoint, nsample, 3
xyz1_expanded = tf.expand_dims(xyz1, 2) # batch_size, npoint, 1, 3
xyz_diff = xyz2_grouped - xyz1_expanded # batch_size, npoint, nsample, 3
feat2_grouped = group_point(feat2, idx) # batch_size, npoint, nsample, channel
feat1_expanded = tf.expand_dims(feat1, 2) # batch_size, npoint, 1, channel
feat_diff = feat2_grouped - feat1_expanded
feat_diff = tf.concat(axis=-1, values=[feat_diff, feat2_grouped, tf.tile(feat1_expanded,[1,1,nsample,1])]) # batch_size, npoint, nsample, channel*2
feat1_new = tf.concat([feat_diff, xyz_diff], axis=3) # batch_size, npoint, nsample, [channel or 1] + 3
# TODO: move scope to outer indent
o=[]
with tf.variable_scope(scope) as sc:
for i, num_out_channel in enumerate(mlp):
activation_fn = tf.nn.relu if i < len(mlp)-1 else None
feat1_new = tf_util.conv2d(feat1_new, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training, #activation_fn=activation_fn,
scope='conv_diff_%d'%(i), bn_decay=bn_decay)
o.append(feat1_new)
feat1_new += 0.00001
feat1_new = tf.squeeze(feat1_new, [3]) # batch_size, npoint1, nsample
square = feat1_new #tf.square(feat1_new)
sm = square / tf.expand_dims(tf.reduce_sum(square, axis=-1), axis=-1)
# sm = tf.nn.softmax(feat1_new) # batch_size, npoint1, nsample
sm = tf.expand_dims(sm, axis=-1)
flow_new = xyz_diff * sm # batch_size, npoint, nsample, 3
flow_new = tf.reduce_sum(flow_new, axis=-2) # batch_size, npoint, 3
# feat_new = feat2_grouped * sm # batch_size, npoint, nsample, channel
# feat_new = tf.reduce_sum(feat_new, axis=-2) # batch_size, npoint, channel
return xyz1, flow_new, sm, idx,o, feat_diff, xyz_diff
def sample_and_group(self, xyz, points):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
# 每个batch取样的最远的1024个点
# new_xyz: b * npoints * 3
new_xyz = gather_point(xyz, farthest_point_sample(
self.npoint, xyz)) # (batch_size, npoint, 3)
if self.knn:
_, idx = knn_point(self.nsample, xyz, new_xyz)
else:
# idx: (batch_size, npoint, nsample) int32 array, indices to input points
# pts_cnt: (batch_size, npoint) int32 array, number of unique points in each local region
idx, pts_cnt = query_ball_point(self.radius, self.nsample, xyz,
new_xyz)
# grouped_xyz: (batch_size, npoint, nsample, channel)
# according to idx return corresponding chanel
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
# move the points to the center (by minusing the coordinate of the center)
grouped_xyz -= tf.tile(tf.expand_dims(
new_xyz, 2), [1, 1, self.nsample, 1]) # translation normalization
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if self.use_xyz:
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group_polygons(npoint, nsample, xyz, points):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
# find seed points
new_xyz_idx = farthest_point_sample(npoint, xyz) # (batch_size, npoint)
new_xyz = gather_point(xyz, new_xyz_idx) # (batch_size, npoint, 3)
# find nearest neighbors and group points
_, idx = knn_point(nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz = tf.concat((grouped_xyz, tf.expand_dims(new_xyz, axis=2)),
axis=2) # (batch_size, npoint, nsample+1, 3)
# concatenate the indices of the neighbors to the seed indices
idx = tf.concat((idx, tf.expand_dims(new_xyz_idx, axis=-1)), axis=-1)
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample+1, channel)
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample+1, 3+channel)
else:
new_points = grouped_xyz
return new_xyz, new_points, grouped_xyz
def sample_and_group(npoint, radius, nsample, xyz, points, global_idx, knn=False, use_xyz=True):
fps_idx, g_idx = farthest_point_sample(npoint, xyz, global_idx)
new_xyz = gather_point(xyz, fps_idx) # (batch_size, npoint, 3)
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
center_xyz = tf.tile(tf.expand_dims(new_xyz, 2), [1, 1, nsample, 1])
diff_xyz = grouped_xyz - center_xyz # translation normalization
euclid_dist = tf.norm(diff_xyz, axis=-1, keep_dims=True)
grouped_xyz = tf.concat([grouped_xyz, center_xyz, diff_xyz, euclid_dist], axis=-1)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat([diff_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = diff_xyz
return new_xyz, new_points, fps_idx, g_idx, diff_xyz
def sample_edge(npoint, radius, nsample, xyz, points):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_edge(xyz, farthest_point_sample(npoint, xyz))
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz))
if knn:
#print('using knn')
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2),
[1, 1, nsample, 1]) # translation normalization
#print('grouped points',grouped_xyz.shape)
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
#print('new points',new_points.shape)
return new_xyz, new_points, idx, grouped_xyz
def sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec=None, knn=False, use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
tnet_spec: dict (keys: mlp, mlp2, is_training, bn_decay), if None do not apply tnet
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
#npoint个采样点，每个采样点周围采样nsample个点 #sampling layer
new_xyz = gather_point(xyz, farthest_point_sample(npoint, xyz)) # (batch_size, npoint, 3)
# grouping layer
if knn:
_,idx = knn_point(nsample, xyz, new_xyz)
else: #idx应该是用数字表示是第几个shape的第几个点周围的neightbor，也就是一个sample内部的序号
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3) #把sample的内部序号和点的序号对应的坐标组合起来
#每个点和中心点的相对距离
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2), [1,1,nsample,1]) # translation normalization 对每个npoint插入一维，大小是nsample，值和中间点一样。
if tnet_spec is not None:
grouped_xyz = tnet(grouped_xyz, tnet_spec)
if points is not None:
grouped_points = group_point(points, idx) # (batch_size, npoint, nsample, channel)#points是一些featrue，xyz才是坐标
if use_xyz:
new_points = tf.concat([grouped_xyz, grouped_points], axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz #中心点，分组后的点（可能包含channel），idx和分组后的xyz
def sample_and_group_all_polygons(nsample, xyz, points):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
ndataset = xyz.get_shape()[1].value
# find nearest neighbors and group points
_, idx = knn_point(nsample, xyz, xyz)
grouped_xyz = group_point(xyz, idx) # (batch_size, ndataset, nsample, 3)
grouped_xyz = tf.concat((tf.expand_dims(xyz, axis=2), grouped_xyz),
axis=2) # (batch_size, ndataset, nsample+1, 3)
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, ndataset, nsample, channel)
grouped_points = tf.concat(
(tf.expand_dims(points, axis=2), grouped_points),
axis=2) # (batch_size, ndataset, nsample+1, channel)
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample+1, 3+channel)
else:
new_points = grouped_xyz
return xyz, new_points, grouped_xyz
def pointnet_sa_module_msg3(gt,
pred,
npoint,
radius_list,
nsample_list,
mlp_list,
scope,
use_xyz=True,
use_nchw=False,
knn=True):
''' PointNet Set Abstraction (SA) module with Multi-Scale Grouping (MSG)
Input:
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor
npoint: int32 -- #points sampled in farthest point sampling
radius: list of float32 -- search radius in local region
nsample: list of int32 -- how many points in each local region
mlp: list of list of int32 -- output size for MLP on each point
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
use_nchw: bool, if True, use NCHW data format for conv2d, which is usually faster than NHWC format
Return:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, \sum_k{mlp[k][-1]}) TF tensor
'''
with tf.variable_scope(scope) as sc:
p1_idx = farthest_point_sample(npoint, gt)
source_gt = gather_point(gt, p1_idx)
new_points_list = []
for i in range(len(radius_list)):
radius = radius_list[i]
nsample = nsample_list[i]
if knn:
_, idx_gt = knn_point(nsample, gt, source_gt)
else:
idx_gt, _ = query_ball_point(radius, nsample, gt, source_gt)
grouped_gt = group_point(gt, idx_gt) #b*n*k*3
grouped_gt -= tf.tile(tf.expand_dims(source_gt, 2),
[1, 1, nsample, 1])
if knn:
_, idx_pred = knn_point(nsample, pred, source_gt)
else:
idx_pred, _ = query_ball_point(radius, nsample, pred,
source_gt)
grouped_pred = group_point(pred, idx_pred) # b*n*k*3
grouped_pred -= tf.tile(tf.expand_dims(source_gt, 2),
[1, 1, nsample, 1])
grouped_points = tf.concat([grouped_gt, grouped_pred], axis=2)
for j, num_out_channel in enumerate(mlp_list[i]):
grouped_points = conv2d(grouped_points,
num_out_channel, [1, 1],
weight_decay=0,
padding='VALID',
stride=[1, 1],
scope='conv%d_%d' % (i, j),
activation_fn=tf.nn.leaky_relu)
#new_points = tf.reduce_max(grouped_points, axis=[2]) #b*n*c
new_points = tf.layers.max_pooling2d(grouped_points, [1, nsample],
strides=[1, nsample],
padding='VALID',
name='maxpool_%d' % i)
new_points_list.append(new_points)
new_points_concat = tf.concat(new_points_list, axis=-1)
return source_gt, new_points_concat
def sample_and_group(npoint,
radius,
nsample,
xyz,
points,
knn=False,
use_xyz=True):
'''
Input:
npoint: int32
radius: float32
nsample: int32
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor, if None will just use xyz as points
knn: bool, if True use kNN instead of radius search
use_xyz: bool, if True concat XYZ with local point features, otherwise just use point features
Output:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, nsample, 3+channel) TF tensor
idx: (batch_size, npoint, nsample) TF tensor, indices of local points as in ndataset points
grouped_xyz: (batch_size, npoint, nsample, 3) TF tensor, normalized point XYZs
(subtracted by seed point XYZ) in local regions
'''
new_xyz = gather_point(xyz, farthest_point_sample(
npoint, xyz)) # (batch_size, npoint, 3) B*N*3
if knn:
_, idx = knn_point(nsample, xyz, new_xyz)
else:
idx, pts_cnt = query_ball_point(radius, nsample, xyz, new_xyz)
# idx (batch_size, npoint, nsample) pts_cnt (batch_size, npoint)
grouped_xyz = group_point(xyz, idx) # (batch_size, npoint, nsample, 3)
G_p = get_neigh_geo_feat(new_xyz, grouped_xyz, nsample) # B * N * 32 *12
# batch= xyz.get_shape()[0].value
# one=tf.ones([batch,npoint],dtype=tf.float32)
# V=tf.constant(4/3*math.pi*radius*radius*radius)
#
# D=tf.divide(tf.cast(pts_cnt,tf.float32),tf.cast(V,tf.float32)) # (batch_size, npoint) maybe need to be normalized
# D=tf.expand_dims(D, -1)
# D = tf.tile(tf.expand_dims(D, -1), [1, 1, nsample, 1]) # 16,1024,32,1
#
# G_p=tf.concat([G_p,D], axis=-1) # 16,10244,32,13
# now, grouped_xyz is local coordinate
grouped_xyz -= tf.tile(tf.expand_dims(new_xyz, 2),
[1, 1, nsample, 1]) # translation normalization
if points is not None:
grouped_points = group_point(
points, idx) # (batch_size, npoint, nsample, channel)
if use_xyz:
new_points = tf.concat(
[grouped_xyz, grouped_points],
axis=-1) # (batch_size, npoint, nample, 3+channel)
else:
new_points = grouped_points
else:
new_points = grouped_xyz
return new_xyz, new_points, idx, grouped_xyz, G_p
def get_model(xyz, is_training, bn_decay=None, num_class=NUM_CLASSES):
batch_size = xyz.get_shape()[0].value
num_point = xyz.get_shape()[1].value
nsample = 20
G = 16
taylor_channel = 5
with tf.variable_scope('delta') as sc:
_, idx = knn_point(nsample, xyz, xyz)
grouped_xyz = group_point(xyz, idx)
point_cloud_tile = tf.expand_dims(xyz, [2])
point_cloud_tile = tf.tile(point_cloud_tile, [1, 1, nsample, 1])
delta = grouped_xyz - point_cloud_tile
with tf.variable_scope('fanConv1') as sc:
feat_1 = tf_util.spiderConv(xyz,
idx,
delta,
32,
taylor_channel=taylor_channel,
gn=True,
G=G,
is_multi_GPU=True)
with tf.variable_scope('fanConv2') as sc:
feat_2 = tf_util.spiderConv(feat_1,
idx,
delta,
64,
taylor_channel=taylor_channel,
gn=True,
G=G,
is_multi_GPU=True)
with tf.variable_scope('fanConv3') as sc:
feat_3 = tf_util.spiderConv(feat_2,
idx,
delta,
128,
taylor_channel=taylor_channel,
gn=True,
G=G,
is_multi_GPU=True)
with tf.variable_scope('fanConv4') as sc:
feat_4 = tf_util.spiderConv(feat_3,
idx,
delta,
256,
taylor_channel=taylor_channel,
gn=True,
G=G,
is_multi_GPU=True)
feat = tf.concat([feat_1, feat_2, feat_3, feat_4], 2)
#top-k pooling
net = tf_util.topk_pool(feat, k=2, scope='topk_pool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net,
1024,
bn=True,
is_training=is_training,
scope='fc1',
bn_decay=bn_decay,
is_multi_GPU=True)
net = tf_util.dropout(net,
keep_prob=0.3,
is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net,
512,
bn=True,
is_training=is_training,
scope='fc2',
bn_decay=bn_decay,
is_multi_GPU=True)
net = tf_util.dropout(net,
keep_prob=0.3,
is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net,
num_class,
activation_fn=None,
scope='fc3')
return net
def get_model(xyz_withnor, is_training, bn_decay=None, num_classes=40):
batch_size = xyz_withnor.get_shape()[0].value
num_point = xyz_withnor.get_shape()[1].value
K_knn = 20
taylor_channel = 3
xyz = xyz_withnor[:, :, 0:3]
with tf.variable_scope('delta') as sc:
_, idx = knn_point(K_knn, xyz, xyz)
grouped_xyz = group_point(xyz, idx)
point_cloud_tile = tf.expand_dims(xyz, [2])
point_cloud_tile = tf.tile(point_cloud_tile, [1, 1, K_knn, 1])
delta = grouped_xyz - point_cloud_tile
with tf.variable_scope('SpiderConv1') as sc:
feat_1 = tf_util.spiderConv(xyz_withnor,
idx,
delta,
32,
taylor_channel=taylor_channel,
bn=True,
is_training=is_training,
bn_decay=bn_decay)
with tf.variable_scope('SpiderConv2') as sc:
feat_2 = tf_util.spiderConv(feat_1,
idx,
delta,
64,
taylor_channel=taylor_channel,
bn=True,
is_training=is_training,
bn_decay=bn_decay)
with tf.variable_scope('SpiderConv3') as sc:
feat_3 = tf_util.spiderConv(feat_2,
idx,
delta,
128,
taylor_channel=taylor_channel,
bn=True,
is_training=is_training,
bn_decay=bn_decay)
with tf.variable_scope('SpiderConv4') as sc:
feat_4 = tf_util.spiderConv(feat_3,
idx,
delta,
256,
taylor_channel=taylor_channel,
bn=True,
is_training=is_training,
bn_decay=bn_decay)
feat = tf.concat([feat_1, feat_2, feat_3, feat_4], 2)
#top-k pooling
net = tf_util.topk_pool(feat, k=2, scope='topk_pool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net,
512,
bn=True,
is_training=is_training,
scope='fc1',
bn_decay=bn_decay)
net = tf_util.dropout(net,
keep_prob=0.5,
is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net,
256,
bn=True,
is_training=is_training,
scope='fc2',
bn_decay=bn_decay)
net = tf_util.dropout(net,
keep_prob=0.5,
is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net, 40, activation_fn=None, scope='fc3')
return net
