Python tf_util.max_pool2d方法代碼示例

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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 

# 需要導入模塊: import tf_util [as 別名]
# 或者: from tf_util import max_pool2d [as 別名]
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