Python tf_util.max_pool2d() Examples
The following are 30
code examples of tf_util.max_pool2d().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tf_util
, or try the search function
.
.
Example #1
| Source File: tp8.py From AlignNet-3D with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def _get_dgcnn(pcs, layer_sizes, scope_name, is_training, bn_decay):
assert len(layer_sizes) > 0
num_point = pcs.shape[1]
k = 20
with tf.variable_scope(scope_name):
adj_matrix = tf_util_dgcnn.pairwise_distance(pcs)
nn_idx = tf_util_dgcnn.knn(adj_matrix, k=k)
edge_feature = tf_util_dgcnn.get_edge_feature(pcs, nn_idx=nn_idx, k=k)
net = tf_util_dgcnn.conv2d(edge_feature, layer_sizes[0], [1, 1], padding='VALID', stride=[1, 1], bn=True, is_training=is_training, scope='conv1', bn_decay=bn_decay)
for idx, layer_size in enumerate(layer_sizes[1:-1]):
net = tf_util_dgcnn.conv2d(net, layer_size, [1, 1], padding='VALID', stride=[1, 1], bn=True, is_training=is_training, scope=f'conv{idx+2}', bn_decay=bn_decay)
net = tf.reduce_max(net, axis=-2, keepdims=True)
net = tf_util_dgcnn.conv2d(net, layer_sizes[-1], [1, 1], padding='VALID', stride=[1, 1], bn=True, is_training=is_training, scope=f'conv{len(layer_sizes)}', bn_decay=bn_decay)
net = tf_util_dgcnn.max_pool2d(net, [num_point, 1], padding='VALID', scope='maxpool')
return net
Example #2
| Source File: pcr_model.py From pointnet-registration-framework with MIT License | 5 votes |
|
def get_model(self, source_point_cloud, template_point_cloud, feature_size, is_training, bn_decay=None):
point_cloud = tf.concat([source_point_cloud, template_point_cloud], 0)
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, feature_size, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
net = tf.reshape(net, [batch_size, -1])
# Extract the features from the network.
source_global_feature = tf.slice(net, [0,0], [int(batch_size/2),feature_size])
template_global_feature = tf.slice(net, [int(batch_size/2),0], [int(batch_size/2),feature_size])
return source_global_feature, template_global_feature
Example #3
| Source File: pointnet.py From DBNet with Apache License 2.0 | 5 votes |
|
def get_model(point_cloud, is_training, bn_decay=None):
""" Classification PointNet, input is BxNx3, output Bx40 """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
# Point functions (MLP implemented as conv2d)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
# MLP on global point cloud vector
net = tf.reshape(net, [batch_size, -1])
return net
Example #4
| Source File: model_util.py From frustum-pointnets with Apache License 2.0 | 5 votes |
|
def get_center_regression_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' Regression network for center delta. a.k.a. T-Net.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in 3D mask coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
predicted_center: TF tensor in shape (B,3)
'''
num_point = object_point_cloud.get_shape()[1].value
net = tf.expand_dims(object_point_cloud, 2)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg1-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg2-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg3-stage1', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool-stage1')
net = tf.squeeze(net, axis=[1,2])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 256, scope='fc1-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, scope='fc2-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
predicted_center = tf_util.fully_connected(net, 3, activation_fn=None,
scope='fc3-stage1')
return predicted_center, end_points
Example #5
| Source File: pointnet_plane_detection2.py From PointNet-Plane-Detection with GNU General Public License v3.0 | 5 votes |
|
def get_transform(point_cloud, is_training, bn_decay=None, K = 3):
""" Transform Net, input is BxNx3 gray image
Return:
Transformation matrix of size 3xK """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv4', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1], padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_XYZ') as sc:
assert(K==3)
weights = tf.get_variable('weights', [128, 3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32)
biases = tf.get_variable('biases', [3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32) + tf.constant([1,0,0,0,1,0,0,0,1], dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
#transform = tf_util.fully_connected(net, 3*K, activation_fn=None, scope='tfc3')
transform = tf.reshape(transform, [batch_size, 3, K])
return transform
Example #6
| Source File: pointnet_plane_detection2.py From PointNet-Plane-Detection with GNU General Public License v3.0 | 5 votes |
|
def get_transform_K(inputs, is_training, bn_decay=None, K = 3):
""" Transform Net, input is BxNx1xK gray image
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 256, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv2', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1], padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training, scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training, scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32)
biases = tf.get_variable('biases', [K*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32) + tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
#transform = tf_util.fully_connected(net, 3*K, activation_fn=None, scope='tfc3')
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #7
| Source File: pointnet_plane_detection.py From PointNet-Plane-Detection with GNU General Public License v3.0 | 5 votes |
|
def get_transform(point_cloud, is_training, bn_decay=None, K = 3):
""" Transform Net, input is BxNx3 gray image
Return:
Transformation matrix of size 3xK """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv4', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1], padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_XYZ') as sc:
assert(K==3)
weights = tf.get_variable('weights', [128, 3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32)
biases = tf.get_variable('biases', [3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32) + tf.constant([1,0,0,0,1,0,0,0,1], dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
#transform = tf_util.fully_connected(net, 3*K, activation_fn=None, scope='tfc3')
transform = tf.reshape(transform, [batch_size, 3, K])
return transform
Example #8
| Source File: pointnet_plane_detection.py From PointNet-Plane-Detection with GNU General Public License v3.0 | 5 votes |
|
def get_transform_K(inputs, is_training, bn_decay=None, K = 3):
""" Transform Net, input is BxNx1xK gray image
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 256, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv2', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1], padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training, scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training, scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32)
biases = tf.get_variable('biases', [K*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32) + tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
#transform = tf_util.fully_connected(net, 3*K, activation_fn=None, scope='tfc3')
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #9
| Source File: transform_nets.py From 3d-adv-pc with MIT License | 5 votes |
|
def feature_transform_net(inputs, is_training, bn_decay=None, K=64):
""" Feature Transform Net, input is BxNx1xK
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #10
| Source File: pcr_model.py From pcrnet with MIT License | 5 votes |
|
def get_model(self, source_point_cloud, template_point_cloud, feature_size, is_training, bn_decay=None):
point_cloud = tf.concat([source_point_cloud, template_point_cloud], 0)
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, feature_size, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
net = tf.reshape(net, [batch_size, -1])
# Extract the features from the network.
source_global_feature = tf.slice(net, [0,0], [int(batch_size/2),feature_size])
template_global_feature = tf.slice(net, [int(batch_size/2),0], [int(batch_size/2),feature_size])
return source_global_feature, template_global_feature
Example #11
| Source File: ipcr_model.py From pcrnet with MIT License | 5 votes |
|
def get_model(source_point_cloud, template_point_cloud, is_training, bn_decay=None):
point_cloud = tf.concat([source_point_cloud, template_point_cloud],0)
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
net = tf.reshape(net, [batch_size, -1])
source_global_feature = tf.slice(net, [0,0], [int(batch_size/2),1024])
template_global_feature = tf.slice(net, [int(batch_size/2),0], [int(batch_size/2),1024])
return source_global_feature, template_global_feature
Example #12
| Source File: model.py From deep_gcns with MIT License | 5 votes |
|
def build_fusion_block(self, graphs, num_vertices):
out = self.mlp_builder.build(tf.concat(graphs, axis=-1),
1024,
scope='adj_conv_'+'final',
is_training=self.is_training)
out_max = tf_util.max_pool2d(out, [num_vertices, 1], padding='VALID', scope='maxpool')
expand = tf.tile(out_max, [1, num_vertices, 1, 1])
fusion = tf.concat(axis=3, values=[expand]+graphs)
return fusion
Example #13
| Source File: pointnet_part_seg.py From PointCNN.Pytorch with MIT License | 5 votes |
|
def get_transform(point_cloud, is_training, bn_decay=None, K = 3):
""" Transform Net, input is BxNx3 gray image
Return:
Transformation matrix of size 3xK """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='tconv4', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1], padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, bn=True, is_training=is_training, scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_XYZ') as sc:
assert(K==3)
weights = tf.get_variable('weights', [128, 3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32)
biases = tf.get_variable('biases', [3*K], initializer=tf.constant_initializer(0.0), dtype=tf.float32) + tf.constant([1,0,0,0,1,0,0,0,1], dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
#transform = tf_util.fully_connected(net, 3*K, activation_fn=None, scope='tfc3')
transform = tf.reshape(transform, [batch_size, 3, K])
return transform
Example #14
| Source File: model.py From PointCNN.Pytorch with MIT License | 5 votes |
|
def get_model(point_cloud, is_training, bn_decay=None):
""" ConvNet baseline, input is BxNx3 gray image """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
# CONV
net = tf_util.conv2d(input_image, 64, [1,9], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv4', bn_decay=bn_decay)
points_feat1 = tf_util.conv2d(net, 1024, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv5', bn_decay=bn_decay)
# MAX
pc_feat1 = tf_util.max_pool2d(points_feat1, [num_point,1], padding='VALID', scope='maxpool1')
# FC
pc_feat1 = tf.reshape(pc_feat1, [batch_size, -1])
pc_feat1 = tf_util.fully_connected(pc_feat1, 256, bn=True, is_training=is_training, scope='fc1', bn_decay=bn_decay)
pc_feat1 = tf_util.fully_connected(pc_feat1, 128, bn=True, is_training=is_training, scope='fc2', bn_decay=bn_decay)
print(pc_feat1)
# CONCAT
pc_feat1_expand = tf.tile(tf.reshape(pc_feat1, [batch_size, 1, 1, -1]), [1, num_point, 1, 1])
points_feat1_concat = tf.concat(axis=3, values=[points_feat1, pc_feat1_expand])
# CONV
net = tf_util.conv2d(points_feat1_concat, 512, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv6')
net = tf_util.conv2d(net, 256, [1,1], padding='VALID', stride=[1,1],
bn=True, is_training=is_training, scope='conv7')
net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training, scope='dp1')
net = tf_util.conv2d(net, 13, [1,1], padding='VALID', stride=[1,1],
activation_fn=None, scope='conv8')
net = tf.squeeze(net, [2])
return net
Example #15
| Source File: transform_nets.py From PointCNN.Pytorch with MIT License | 5 votes |
|
def feature_transform_net(inputs, is_training, bn_decay=None, K=64):
""" Feature Transform Net, input is BxNx1xK
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #16
| Source File: transform_nets.py From scanobjectnn with MIT License | 5 votes |
|
def feature_transform_net(inputs, is_training, bn_decay=None, K=64):
""" Feature Transform Net, input is BxNx1xK
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #17
| Source File: transform_nets.py From pointnetvlad with MIT License | 5 votes |
|
def feature_transform_net(inputs, is_training, bn_decay=None, K=64):
""" Feature Transform Net, input is BxNx1xK
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #18
| Source File: ipcr_model.py From pointnet-registration-framework with MIT License | 5 votes |
|
def get_model(source_point_cloud, template_point_cloud, is_training, bn_decay=None):
point_cloud = tf.concat([source_point_cloud, template_point_cloud],0)
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=False, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
net = tf.reshape(net, [batch_size, -1])
source_global_feature = tf.slice(net, [0,0], [int(batch_size/2),1024])
template_global_feature = tf.slice(net, [int(batch_size/2),0], [int(batch_size/2),1024])
return source_global_feature, template_global_feature
Example #19
| Source File: transform_nets.py From deep-functional-dictionaries with MIT License | 5 votes |
|
def feature_transform_net(inputs, is_training, bn_decay=None, K=64):
""" Feature Transform Net, input is BxNx1xK
Return:
Transformation matrix of size KxK """
batch_size = inputs.get_shape()[0].value
num_point = inputs.get_shape()[1].value
net = tf_util.conv2d(inputs, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_feat') as sc:
weights = tf.get_variable('weights', [256, K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [K*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant(np.eye(K).flatten(), dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, K, K])
return transform
Example #20
| Source File: tp8.py From AlignNet-3D with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def _get_pointnet(pcs_extended, layer_sizes, scope_name, is_training, bn_decay):
assert len(layer_sizes) > 0
num_point = pcs_extended.shape[1]
num_channel = pcs_extended.shape[2]
with tf.variable_scope(scope_name):
# Point functions (MLP implemented as conv2d)
net = tf_util.conv2d(pcs_extended, layer_sizes[0], [1, num_channel], padding='VALID', stride=[1, 1], bn=True, is_training=is_training, scope='conv1', bn_decay=bn_decay)
for idx, layer_size in enumerate(layer_sizes[1:]):
net = tf_util.conv2d(net, layer_size, [1, 1], padding='VALID', stride=[1, 1], bn=True, is_training=is_training, scope=f'conv{idx+2}', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point, 1], padding='VALID', scope='maxpool')
return net
Example #21
| Source File: model_util.py From Geo-CNN with Apache License 2.0 | 5 votes |
|
def get_center_regression_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' Regression network for center delta. a.k.a. T-Net.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in 3D mask coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
predicted_center: TF tensor in shape (B,3)
'''
num_point = object_point_cloud.get_shape()[1].value
net = tf.expand_dims(object_point_cloud, 2)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg1-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg2-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg3-stage1', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool-stage1')
net = tf.squeeze(net, axis=[1,2])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 256, scope='fc1-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, scope='fc2-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
predicted_center = tf_util.fully_connected(net, 3, activation_fn=None,
scope='fc3-stage1')
return predicted_center, end_points
Example #22
| Source File: frustum_geocnn_v1.py From Geo-CNN with Apache License 2.0 | 5 votes |
|
def get_3d_box_estimation_v1_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' 3D Box Estimation PointNet v1 network.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in object coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
output: TF tensor in shape (B,3+NUM_HEADING_BIN*2+NUM_SIZE_CLUSTER*4)
including box centers, heading bin class scores and residuals,
and size cluster scores and residuals
'''
num_point = object_point_cloud.get_shape()[1].value
net = tf_util.perceptron(object_point_cloud, 128,
bn=True, is_training=is_training,
scope='conv-reg1', bn_decay=bn_decay)
net = tf_util.perceptron(net, 128,
bn=True, is_training=is_training,
scope='conv-reg2', bn_decay=bn_decay)
net = tf_util.perceptron(net, 256,
bn=True, is_training=is_training,
scope='conv-reg3', bn_decay=bn_decay)
net = tf_util.perceptron(net, 512,
bn=True, is_training=is_training,
scope='conv-reg4', bn_decay=bn_decay)
net = tf_util.max_pool2d(tf.expand_dims(net, 3), [num_point,1],
padding='VALID', scope='maxpool2')
net = tf.squeeze(net, axis=[1, 3])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 512, scope='fc1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, scope='fc2', bn=True,
is_training=is_training, bn_decay=bn_decay)
# The first 3 numbers: box center coordinates (cx,cy,cz),
# the next NUM_HEADING_BIN*2: heading bin class scores and bin residuals
# next NUM_SIZE_CLUSTER*4: box cluster scores and residuals
output = tf_util.fully_connected(net,
3+NUM_HEADING_BIN*2+NUM_SIZE_CLUSTER*4, activation_fn=None, scope='fc3')
return output, end_points
Example #23
| Source File: pointnet.py From SGPN with MIT License | 5 votes |
|
def get_model(point_cloud, is_training, bn=True, bn_decay=None):
""" ConvNet baseline, input is BxNx9 gray image """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
# CONV
net = tf_util.conv2d(input_image, 64, [1, 9], padding='VALID', stride=[1, 1],
bn=bn, is_training=is_training, scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1, 1], padding='VALID', stride=[1, 1],
bn=bn, is_training=is_training, scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1, 1], padding='VALID', stride=[1, 1],
bn=bn, is_training=is_training, scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1, 1], padding='VALID', stride=[1, 1],
bn=bn, is_training=is_training, scope='conv4', bn_decay=bn_decay)
points_feat1 = tf_util.conv2d(net, 1024, [1, 1], padding='VALID', stride=[1, 1],
bn=bn, is_training=is_training, scope='conv5', bn_decay=bn_decay)
# MAX
pc_feat1 = tf_util.max_pool2d(points_feat1, [num_point, 1], padding='VALID', scope='maxpool1')
# FC
pc_feat1 = tf.reshape(pc_feat1, [batch_size, -1])
pc_feat1 = tf_util.fully_connected(pc_feat1, 256, bn=bn, is_training=is_training, scope='fc1', bn_decay=bn_decay)
pc_feat1 = tf_util.fully_connected(pc_feat1, 128, bn=bn, is_training=is_training, scope='fc2', bn_decay=bn_decay)
# print(pc_feat1)
# CONCAT
pc_feat1_expand = tf.tile(tf.reshape(pc_feat1, [batch_size, 1, 1, -1]), [1, num_point, 1, 1])
points_feat1_concat = tf.concat(axis=3, values=[points_feat1, pc_feat1_expand])
# CONV
net = tf_util.conv2d(points_feat1_concat, 512, [1, 1], padding='VALID', stride=[1, 1], bn=bn, is_training=is_training, scope='conv6')
net = tf_util.conv2d(net, 256, [1, 1], padding='VALID', stride=[1, 1], bn=bn, is_training=is_training, scope='conv7')
# net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training, scope='dp1')
# net = tf_util.conv2d(net, 13, [1, 1], padding='VALID', stride=[1, 1],
# activation_fn=None, scope='conv8')
# net = tf.squeeze(net, [2])
return net
Example #24
| Source File: model_util.py From reading-frustum-pointnets-code with Apache License 2.0 | 5 votes |
|
def get_center_regression_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' Regression network for center delta. a.k.a. T-Net.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in 3D mask coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
predicted_center: TF tensor in shape (B,3)
'''
num_point = object_point_cloud.get_shape()[1].value#M
net = tf.expand_dims(object_point_cloud, 2)#(B,M,1,C)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg1-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg2-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg3-stage1', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool-stage1')
net = tf.squeeze(net, axis=[1,2])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 256, scope='fc1-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, scope='fc2-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
predicted_center = tf_util.fully_connected(net, 3, activation_fn=None,
scope='fc3-stage1')
return predicted_center, end_points
Example #25
| Source File: model_util.py From tf-3d-object-detection with MIT License | 5 votes |
|
def get_center_regression_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' Regression network for center delta. a.k.a. T-Net.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in 3D mask coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
predicted_center: TF tensor in shape (B,3)
'''
num_point = object_point_cloud.get_shape()[1].value
net = tf.expand_dims(object_point_cloud, 2)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg1-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg2-stage1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg3-stage1', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool-stage1')
net = tf.squeeze(net, axis=[1,2])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 256, scope='fc1-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 128, scope='fc2-stage1', bn=True,
is_training=is_training, bn_decay=bn_decay)
predicted_center = tf_util.fully_connected(net, 3, activation_fn=None,
scope='fc3-stage1')
return predicted_center, end_points
Example #26
| Source File: pointnet_cls.py From scanobjectnn with MIT License | 4 votes |
|
def get_model(point_cloud, is_training, bn_decay=None, num_class=NUM_CLASSES):
""" Classification PointNet, input is BxNx3, output Bx40 """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
with tf.variable_scope('transform_net1') as sc:
transform = input_transform_net(point_cloud, is_training, bn_decay, K=3)
point_cloud_transformed = tf.matmul(point_cloud, transform)
input_image = tf.expand_dims(point_cloud_transformed, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
with tf.variable_scope('transform_net2') as sc:
transform = feature_transform_net(net, is_training, bn_decay, K=64)
end_points['transform'] = transform
net_transformed = tf.matmul(tf.squeeze(net, axis=[2]), transform)
net_transformed = tf.expand_dims(net_transformed, [2])
net = tf_util.conv2d(net_transformed, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
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=0.7, 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=0.7, is_training=is_training,
scope='dp2')
net = tf_util.fully_connected(net, num_class, activation_fn=None, scope='fc3')
return net, end_points
Example #27
| Source File: pointnet_cls_basic.py From dfc2019 with MIT License | 4 votes |
|
def get_model(point_cloud, is_training, bn_decay=None):
""" Classification PointNet, input is BxNx3, output Bx40 """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
end_points = {}
input_image = tf.expand_dims(point_cloud, -1)
# Point functions (MLP implemented as conv2d)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 64, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv4', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv5', bn_decay=bn_decay)
# Symmetric function: max pooling
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool')
# MLP on global point cloud vector
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.fully_connected(net, 256, bn=True, is_training=is_training,
scope='fc2', bn_decay=bn_decay)
net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training,
scope='dp1')
net = tf_util.fully_connected(net, 40, activation_fn=None, scope='fc3')
return net, end_points
Example #28
| Source File: pointnet_util.py From articulated-part-induction with MIT License | 4 votes |
|
def pointnet_sa_module(xyz, points, npoint, radius, nsample, mlp, mlp2, group_all, is_training, bn_decay, scope, bn=True, pooling='max', tnet_spec=None, knn=False, use_xyz=True, mask=None, centralize_points=False):
''' PointNet Set Abstraction (SA) Module
Input:
xyz: (batch_size, ndataset, 3) TF tensor
points: (batch_size, ndataset, channel) TF tensor
npoint: int32 -- #points sampled in farthest point sampling
radius: float32 -- search radius in local region
nsample: int32 -- how many points in each local region
mlp: list of int32 -- output size for MLP on each point
mlp2: list of int32 -- output size for MLP on each region
group_all: bool -- group all points into one PC if set true, OVERRIDE
npoint, radius and nsample settings
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
idx: (batch_size, npoint, nsample) int32 -- indices for local regions
'''
with tf.variable_scope(scope) as sc:
if group_all:
nsample = xyz.get_shape()[1].value
new_xyz, new_points, idx, grouped_xyz = sample_and_group_all(xyz, points, use_xyz)
else:
new_xyz, new_points, idx, grouped_xyz = sample_and_group(npoint, radius, nsample, xyz, points, tnet_spec, knn, use_xyz, centralize_points)
for i, num_out_channel in enumerate(mlp):
new_points = tf_util.conv2d(new_points, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=bn, is_training=is_training,
scope='conv%d'%(i), bn_decay=bn_decay)
if pooling=='avg':
new_points = tf_util.avg_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='avgpool1')
elif pooling=='weighted_avg':
with tf.variable_scope('weighted_avg1'):
dists = tf.norm(grouped_xyz,axis=-1,ord=2,keep_dims=True)
exp_dists = tf.exp(-dists * 5)
weights = exp_dists/tf.reduce_sum(exp_dists,axis=2,keep_dims=True) # (batch_size, npoint, nsample, 1)
new_points *= weights # (batch_size, npoint, nsample, mlp[-1])
new_points = tf.reduce_sum(new_points, axis=2, keep_dims=True)
elif pooling=='max':
new_points = tf.reduce_max(new_points, axis=[2], keep_dims=True)
elif pooling=='maskmax':
## only used for groupall
# mask (batch_size, npoint)
# new_points (batch_size, 1, npoint, mlp[-1])
mask = tf.expand_dims(tf.expand_dims(mask,1),-1)
new_points = tf.reduce_max(tf.multiply(new_points,mask), axis=[2], keep_dims=True)
elif pooling=='min':
new_points = tf_util.max_pool2d(-1*new_points, [1,nsample], stride=[1,1], padding='VALID', scope='minpool1')
elif pooling=='max_and_avg':
avg_points = tf_util.max_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='maxpool1')
max_points = tf_util.avg_pool2d(new_points, [1,nsample], stride=[1,1], padding='VALID', scope='avgpool1')
new_points = tf.concat([avg_points, max_points], axis=-1)
if mlp2 is None: mlp2 = []
for i, num_out_channel in enumerate(mlp2):
new_points = tf_util.conv2d(new_points, num_out_channel, [1,1],
padding='VALID', stride=[1,1],
bn=bn, is_training=is_training,
scope='conv_post_%d'%(i), bn_decay=bn_decay)
new_points = tf.squeeze(new_points, [2]) # (batch_size, npoints, mlp2[-1])
return new_xyz, new_points, idx
Example #29
| Source File: frustum_pointnets_v1.py From frustum-pointnets with Apache License 2.0 | 4 votes |
|
def get_3d_box_estimation_v1_net(object_point_cloud, one_hot_vec,
is_training, bn_decay, end_points):
''' 3D Box Estimation PointNet v1 network.
Input:
object_point_cloud: TF tensor in shape (B,M,C)
point clouds in object coordinate
one_hot_vec: TF tensor in shape (B,3)
length-3 vectors indicating predicted object type
Output:
output: TF tensor in shape (B,3+NUM_HEADING_BIN*2+NUM_SIZE_CLUSTER*4)
including box centers, heading bin class scores and residuals,
and size cluster scores and residuals
'''
num_point = object_point_cloud.get_shape()[1].value
net = tf.expand_dims(object_point_cloud, 2)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 256, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg3', bn_decay=bn_decay)
net = tf_util.conv2d(net, 512, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='conv-reg4', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='maxpool2')
net = tf.squeeze(net, axis=[1,2])
net = tf.concat([net, one_hot_vec], axis=1)
net = tf_util.fully_connected(net, 512, scope='fc1', bn=True,
is_training=is_training, bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, scope='fc2', bn=True,
is_training=is_training, bn_decay=bn_decay)
# The first 3 numbers: box center coordinates (cx,cy,cz),
# the next NUM_HEADING_BIN*2: heading bin class scores and bin residuals
# next NUM_SIZE_CLUSTER*4: box cluster scores and residuals
output = tf_util.fully_connected(net,
3+NUM_HEADING_BIN*2+NUM_SIZE_CLUSTER*4, activation_fn=None, scope='fc3')
return output, end_points
Example #30
| Source File: transform_nets.py From deep-functional-dictionaries with MIT License | 4 votes |
|
def input_transform_net(point_cloud, is_training, bn_decay=None, K=3):
""" Input (XYZ) Transform Net, input is BxNx3 gray image
Return:
Transformation matrix of size 3xK """
batch_size = point_cloud.get_shape()[0].value
num_point = point_cloud.get_shape()[1].value
input_image = tf.expand_dims(point_cloud, -1)
net = tf_util.conv2d(input_image, 64, [1,3],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv1', bn_decay=bn_decay)
net = tf_util.conv2d(net, 128, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv2', bn_decay=bn_decay)
net = tf_util.conv2d(net, 1024, [1,1],
padding='VALID', stride=[1,1],
bn=True, is_training=is_training,
scope='tconv3', bn_decay=bn_decay)
net = tf_util.max_pool2d(net, [num_point,1],
padding='VALID', scope='tmaxpool')
net = tf.reshape(net, [batch_size, -1])
net = tf_util.fully_connected(net, 512, bn=True, is_training=is_training,
scope='tfc1', bn_decay=bn_decay)
net = tf_util.fully_connected(net, 256, bn=True, is_training=is_training,
scope='tfc2', bn_decay=bn_decay)
with tf.variable_scope('transform_XYZ') as sc:
assert(K==3)
weights = tf.get_variable('weights', [256, 3*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases = tf.get_variable('biases', [3*K],
initializer=tf.constant_initializer(0.0),
dtype=tf.float32)
biases += tf.constant([1,0,0,0,1,0,0,0,1], dtype=tf.float32)
transform = tf.matmul(net, weights)
transform = tf.nn.bias_add(transform, biases)
transform = tf.reshape(transform, [batch_size, 3, K])
return transform
