def feature_decoding_layer_depthwise(xyz1,
xyz2,
points1,
points2,
radius,
sigma,
K,
mlp,
is_training,
bn_decay,
weight_decay,
scope,
bn=True,
use_xyz=True):
''' Input:
depthwise version of pointconv
xyz1: (batch_size, ndataset1, 3) TF tensor
xyz2: (batch_size, ndataset2, 3) TF tensor, sparser than xyz1
points1: (batch_size, ndataset1, nchannel1) TF tensor
points2: (batch_size, ndataset2, nchannel2) TF tensor
sigma: float32 -- KDE bandwidth
K: int32 -- how many points in each local region
mlp: list of int32 -- output size for MLP on each point
Return:
new_points: (batch_size, ndataset1, mlp[-1]) TF tensor
'''
with tf.variable_scope(scope) as sc:
dist, idx = three_nn(xyz1, xyz2)
dist = tf.maximum(dist, 1e-10)
norm = tf.reduce_sum((1.0 / dist), axis=2, keep_dims=True)
norm = tf.tile(norm, [1, 1, 3])
weight = (1.0 / dist) / norm
interpolated_points = three_interpolate(points2, idx, weight)
#setup for deConv
grouped_xyz, grouped_feature, idx = pointconv_util.grouping(
interpolated_points, K, xyz1, xyz1, use_xyz=use_xyz)
density = pointconv_util.kernel_density_estimation_ball(
xyz1, radius, sigma)
inverse_density = tf.div(1.0, density)
grouped_density = tf.gather_nd(inverse_density,
idx) # (batch_size, npoint, nsample, 1)
#grouped_density = tf_grouping.group_point(inverse_density, idx)
inverse_max_density = tf.reduce_max(grouped_density,
axis=2,
keep_dims=True)
density_scale = tf.div(grouped_density, inverse_max_density)
#density_scale = tf_grouping.group_point(density, idx)
weight = weight_net(grouped_xyz,
[32, grouped_feature.get_shape()[3].value],
scope='decode_weight_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
density_scale = nonlinear_transform(density_scale, [16, 1],
scope='decode_density_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points = tf.multiply(grouped_feature, density_scale)
new_points = tf.multiply(grouped_feature, weight)
new_points = tf_util.reduce_sum2d_conv(new_points,
axis=2,
scope='fp_sumpool',
bn=True,
bn_decay=bn_decay,
is_training=is_training,
keep_dims=False)
if points1 is not None:
new_points1 = tf.concat(
axis=-1, values=[new_points,
points1]) # B,ndataset1,nchannel1+nchannel2
else:
new_points1 = new_points
new_points1 = tf.expand_dims(new_points1, 2)
for i, num_out_channel in enumerate(mlp):
new_points1 = tf_util.conv2d(new_points1,
num_out_channel, [1, 1],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='conv_%d' % (i),
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points1 = tf.squeeze(new_points1, [2]) # B,ndataset1,mlp[-1]
return new_points1
def feature_encoding_layer_msg(xyz,
feature,
npoint,
radius,
sigma,
K,
mlp,
is_training,
bn_decay,
weight_decay,
scope,
bn=True,
use_xyz=True):
''' Input:
xyz: (batch_size, ndataset, 3) TF tensor
feature: (batch_size, ndataset, channel) TF tensor
npoint: int32 -- #points sampled in farthest point sampling
sigma: float32 -- KDE bandwidth
radius_list: list of radius for local region
K_list: int32 -- list of how many points in each local region
mlp: 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
Return:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, mlp[-1] or mlp2[-1]) TF tensor
'''
radius_list = radius
K_list = K
sigma_list = sigma
num_points = xyz.get_shape()[1]
if num_points == npoint:
new_xyz = xyz
else:
new_xyz = pointconv_util.sampling(npoint, xyz)
new_points_list = []
for i in range(len(radius_list)):
with tf.variable_scope("%s_%d" % (scope, i)) as sc:
radius = radius_list[i]
K = K_list[i]
sigma = sigma_list[i]
grouped_xyz, grouped_feature, idx = pointconv_util.grouping(
feature, K, xyz, new_xyz)
density = pointconv_util.kernel_density_estimation_ball(
xyz, radius, sigma)
inverse_density = tf.div(1.0, density)
grouped_density = tf.gather_nd(
inverse_density, idx) # (batch_size, npoint, nsample, 1)
#grouped_density = tf_grouping.group_point(inverse_density, idx)
inverse_max_density = tf.reduce_max(grouped_density,
axis=2,
keep_dims=True)
density_scale = tf.div(grouped_density, inverse_max_density)
#density_scale = tf_grouping.group_point(density, idx)
for j, num_out_channel in enumerate(mlp):
if j != len(mlp) - 1:
grouped_feature = tf_util.conv2d(grouped_feature,
num_out_channel, [1, 1],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='conv%d' % j,
bn_decay=bn_decay,
weight_decay=weight_decay)
weight = weight_net_hidden(grouped_xyz, [32],
scope='weight_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
density_scale = nonlinear_transform(density_scale, [16, 1],
scope='density_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points = tf.multiply(grouped_feature, density_scale)
new_points = tf.transpose(new_points, [0, 1, 3, 2])
new_points = tf.matmul(new_points, weight)
new_points = tf_util.conv2d(new_points,
mlp[-1],
[1, new_points.get_shape()[2].value],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='after_conv',
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points = tf.squeeze(new_points,
[2]) # (batch_size, npoints, mlp2[-1])
new_points_list.append(new_points)
new_points = tf.concat(new_points_list, axis=-1)
return new_xyz, new_points
def feature_encoding_layer_extra(xyz,
sample_xyz,
feature,
npoint,
radius,
sigma,
K,
mlp,
akc_channel,
is_training,
bn_decay,
weight_decay,
scope,
bn=True,
use_xyz=True):
''' Input:
xyz: (batch_size, ndataset, 3) TF tensor
feature: (batch_size, ndataset, channel) TF tensor
npoint: int32 -- #points sampled in farthest point sampling
sigma: float32 -- KDE bandwidth
K: int32 -- how many points in each local region
mlp: 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
Return:
new_xyz: (batch_size, npoint, 3) TF tensor
new_points: (batch_size, npoint, mlp[-1] or mlp2[-1]) TF tensor
'''
with tf.variable_scope(scope) as sc:
num_points = xyz.get_shape()[1]
if num_points == npoint:
new_xyz = xyz
else:
new_xyz = sample_xyz
if akc_channel is not None:
xyz_4n, feature_4n, idx_4n = pointconv_util.grouping(
feature, 4, xyz, xyz)
xyz_3n = xyz_4n[:, :, 1:4, :]
akc_feature = tf_util.akc(xyz_3n, akc_channel, bn, is_training, 0,
bn_decay, weight_decay)
feature = tf.concat([feature, akc_feature], axis=2)
grouped_xyz, grouped_feature, idx = pointconv_util.grouping(
feature, K, xyz, new_xyz)
density = pointconv_util.kernel_density_estimation_ball(
xyz, radius, sigma)
inverse_density = tf.div(1.0, density)
grouped_density = tf.gather_nd(inverse_density,
idx) # (batch_size, npoint, nsample, 1)
#grouped_density = tf_grouping.group_point(inverse_density, idx)
inverse_max_density = tf.reduce_max(grouped_density,
axis=2,
keepdims=True)
density_scale = tf.div(grouped_density, inverse_max_density)
#density_scale = tf_grouping.group_point(density, idx)
for i, num_out_channel in enumerate(mlp):
if i != len(mlp) - 1:
grouped_feature = tf_util.conv2d(grouped_feature,
num_out_channel, [1, 1],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='conv%d' % (i),
bn_decay=bn_decay,
weight_decay=weight_decay)
weight = weight_net_hidden(grouped_xyz, [32],
scope='weight_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
density_scale = nonlinear_transform(density_scale, [16, 1],
scope='density_net',
is_training=is_training,
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points = tf.multiply(grouped_feature, density_scale)
new_points = tf.transpose(new_points, [0, 1, 3, 2])
new_points = tf.matmul(new_points, weight)
new_points = tf_util.conv2d(new_points,
mlp[-1],
[1, new_points.get_shape()[2].value],
padding='VALID',
stride=[1, 1],
bn=bn,
is_training=is_training,
scope='after_conv',
bn_decay=bn_decay,
weight_decay=weight_decay)
new_points = tf.squeeze(new_points,
[2]) # (batch_size, npoints, mlp2[-1])
return new_xyz, new_points