def create_dense_cell(input_nodes):
"""MLP type 2
Args:
input_nodes (list(Node)): possible inputs of the current cell.
Returns:
Cell: a Cell instance.
"""
cell = Cell(input_nodes)
node = VariableNode(name='N')
node.add_op(Dense(10, tf.nn.relu))
node.add_op(Dense(10, tf.nn.relu))
node.add_op(Dense(10, tf.nn.relu))
node.add_op(Dense(10, tf.nn.relu))
cell.graph.add_edge(input_nodes[0], node)
# Block
block = Block()
block.add_node(node)
cell.add_block(block)
cell.set_outputs()
return cell
def create_structure(input_shape=[(2, ), (2, ), (2, )],
output_shape=(1, ),
*args,
**kwargs):
network = KerasStructure(input_shape, output_shape)
input_nodes = network.input_nodes
cell1 = create_cell_1(input_nodes)
network.add_cell(cell1)
cell2 = create_cell_2([cell1.output])
network.add_cell(cell2)
cell3 = Cell(input_nodes + [cell1.output] + [cell2.output])
cnode = VariableNode(name='SkipCo')
nullNode = ConstantNode(op=Tensor([]), name='None')
cnode.add_op(Connect(cell3.graph, nullNode, cnode)) # SAME
cnode.add_op(Connect(cell3.graph, input_nodes[0], cnode))
cnode.add_op(Connect(cell3.graph, input_nodes[1], cnode))
cnode.add_op(Connect(cell3.graph, input_nodes[2], cnode))
cnode.add_op(Connect(cell3.graph, cell1.output, cnode))
cnode.add_op(Connect(cell3.graph, cell2.output, cnode)) # SAME
cnode.add_op(Connect(cell3.graph, input_nodes, cnode))
cnode.add_op(Connect(cell3.graph, [input_nodes[0], input_nodes[1]], cnode))
cnode.add_op(Connect(cell3.graph, [input_nodes[1], input_nodes[2]], cnode))
cnode.add_op(Connect(cell3.graph, [input_nodes[0], input_nodes[2]], cnode))
block = Block()
block.add_node(cnode)
cell3.add_block(block)
network.add_cell(cell3)
return network
def create_conv_block(input_nodes):
# first node of block
n1 = Node('N1')
for inpt in input_nodes:
n1.add_op(Connect(cell.graph, inpt, n1))
def create_conv_node(name):
n = Node(name)
n.add_op(Identity())
n.add_op(Conv1D(filter_size=3, num_filters=16))
n.add_op(Conv1D(filter_size=5, num_filters=16))
n.add_op(MaxPooling1D(pool_size=3, padding='same'))
n.add_op(MaxPooling1D(pool_size=5, padding='same'))
return n
# second node of block
n2 = create_conv_node('N2')
n3 = create_conv_node('N3')
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block
def create_block():
# first node of block
n1 = Node('N1')
for inpt in input_nodes:
n1.add_op(Connect(cell.graph, inpt, n1))
# second node of block
mlp_op_list = list()
mlp_op_list.append(Identity())
mlp_op_list.append(Dense(5, tf.nn.relu))
mlp_op_list.append(Dense(5, tf.nn.tanh))
mlp_op_list.append(Dense(10, tf.nn.relu))
mlp_op_list.append(Dense(10, tf.nn.tanh))
mlp_op_list.append(Dense(20, tf.nn.relu))
mlp_op_list.append(Dense(20, tf.nn.tanh))
n2 = Node('N2')
for op in mlp_op_list:
n2.add_op(op)
# third node of block
n3 = Node('N3')
for op in dropout_ops:
n3.add_op(op)
# 5 Blocks
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block
def create_cell_1(input_nodes):
"""Create a cell with convolution.
Args:
input_nodes (list(Node)): a list of input_nodes for this cell.
Returns:
Cell: the corresponding cell.
"""
cell = Cell(input_nodes)
def create_block(input_node):
# first node of block
n1 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N1')
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N2')
# third node of the block
n3 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N3')
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block, (n1, n2, n3)
block1, _ = create_block(input_nodes[0])
block2, (vn1, vn2, vn3) = create_block(input_nodes[1])
# first node of block
m_vn1 = MirrorNode(node=vn1)
cell.graph.add_edge(input_nodes[2], m_vn1) # fixed input of current block
# second node of block
m_vn2 = MirrorNode(node=vn2)
# third node of the block
m_vn3 = MirrorNode(node=vn3)
block3 = Block()
block3.add_node(m_vn1)
block3.add_node(m_vn2)
block3.add_node(m_vn3)
block3.add_edge(m_vn1, m_vn2)
block3.add_edge(m_vn2, m_vn3)
cell.add_block(block1)
cell.add_block(block2)
cell.add_block(block3)
# set_cell_output_add(cell)
cell.set_outputs()
return cell
def create_structure(input_shape=[(2,), (2,), (2,)], output_shape=(1,),
num_cell=8, *args, **kwargs):
# , output_op=AddByPadding)
network = KerasStructure(input_shape, output_shape)
input_nodes = network.input_nodes
# CELL 1
cell1 = create_cell_1(input_nodes)
network.add_cell(cell1)
# CELL Middle
inputs_skipco = [input_nodes, input_nodes[0],
input_nodes[1], input_nodes[2], cell1.output]
pred_cell = cell1
n = num_cell
for i in range(n):
cell_i = Cell(input_nodes + [cell1.output])
block1 = create_mlp_block(cell_i, pred_cell.output)
cell_i.add_block(block1)
cnode = VariableNode(name='SkipCo')
nullNode = ConstantNode(op=Tensor([]), name='None')
cnode.add_op(Connect(cell_i.graph, nullNode, cnode)) # SAME
for inpt in inputs_skipco:
cnode.add_op(Connect(cell_i.graph, inpt, cnode))
block2 = Block()
block2.add_node(cnode)
cell_i.add_block(block2)
# set_cell_output_add(cell2)
cell_i.set_outputs()
network.add_cell(cell_i)
# prep. for next iter
inputs_skipco.append(cell_i.output)
pred_cell = cell_i
# CELL LAST
cell_last = Cell([pred_cell.output])
block1 = create_mlp_block(cell_last, pred_cell.output)
cell_last.add_block(block1)
# set_cell_output_add(cell3)
cell_last.set_outputs()
network.add_cell(cell_last)
return network
def create_structure(input_shape=[(2, ), (2, ), (2, )],
output_shape=(1, ),
*args,
**kwargs):
# , output_op=AddByPadding)
network = KerasStructure(input_shape, output_shape)
input_nodes = network.input_nodes
# CELL 1
cell1 = create_cell_1(input_nodes)
network.add_cell(cell1)
# CELL 2
cell2 = Cell(input_nodes + [cell1.output])
block1 = create_mlp_block(cell2, cell1.output)
cell2.add_block(block1)
cnode = VariableNode(name='SkipCo')
nullNode = ConstantNode(op=Tensor([]), name='None')
cnode.add_op(Connect(cell2.graph, nullNode, cnode)) # SAME
cnode.add_op(Connect(cell2.graph, input_nodes[0], cnode))
cnode.add_op(Connect(cell2.graph, input_nodes[1], cnode))
cnode.add_op(Connect(cell2.graph, input_nodes[2], cnode))
cnode.add_op(Connect(cell2.graph, cell1.output, cnode))
cnode.add_op(Connect(cell2.graph, input_nodes, cnode))
cnode.add_op(Connect(cell2.graph, [input_nodes[0], input_nodes[1]], cnode))
cnode.add_op(Connect(cell2.graph, [input_nodes[1], input_nodes[2]], cnode))
cnode.add_op(Connect(cell2.graph, [input_nodes[0], input_nodes[2]], cnode))
block2 = Block()
block2.add_node(cnode)
cell2.add_block(block2)
# set_cell_output_add(cell2)
cell2.set_outputs()
network.add_cell(cell2)
# CELL 3
cell3 = Cell([cell2.output])
block1 = create_mlp_block(cell3, cell2.output)
cell3.add_block(block1)
# set_cell_output_add(cell3)
cell3.set_outputs()
network.add_cell(cell3)
return network
def create_dense_cell_type2(input_nodes):
"""MLP type 2
Args:
input_nodes (list(Node)): possible inputs of the current cell.
Returns:
Cell: a Cell instance.
"""
cell = Cell(input_nodes)
# first node of block
n1 = Node('N_0')
for inpt in input_nodes:
n1.add_op(Connect(cell.graph, inpt, n1))
# second node of block
mlp_op_list = list()
mlp_op_list.append(Identity())
mlp_op_list.append(Dense(5, tf.nn.relu))
mlp_op_list.append(Dense(10, tf.nn.relu))
mlp_op_list.append(Dense(20, tf.nn.relu))
mlp_op_list.append(Dense(40, tf.nn.relu))
mlp_op_list.append(Dense(80, tf.nn.relu))
mlp_op_list.append(Dense(160, tf.nn.relu))
mlp_op_list.append(Dense(320, tf.nn.relu))
n2 = Node('N_1')
for op in mlp_op_list:
n2.add_op(op)
# third
n3 = Node('N_2')
drop_ops = []
drop_ops.extend(dropout_ops)
for op in drop_ops:
n3.add_op(op)
# 1 Blocks
block1 = Block()
block1.add_node(n1)
block1.add_node(n2)
block1.add_node(n3)
block1.add_edge(n1, n2)
block1.add_edge(n2, n3)
cell.add_block(block1)
cell.set_outputs()
return cell
def create_mlp_block(cell, input_node):
# first node of block
n1 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N1')
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N2')
n3 = ConstantNode(op=Dense(1000, tf.nn.relu), name='N3')
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block
def create_block(input_node):
def add_mlp_ops_to(vnode):
# REG_L1 = 1.
# REG_L2 = 1.
# vnode.add_op(Identity())
# vnode.add_op(Dense(100, tf.nn.relu))
# vnode.add_op(Dense(100, tf.nn.tanh))
# vnode.add_op(Dense(100, tf.nn.sigmoid))
# vnode.add_op(Dropout(0.05))
# vnode.add_op(Dense(500, tf.nn.relu))
# vnode.add_op(Dense(500, tf.nn.tanh))
# vnode.add_op(Dense(500, tf.nn.sigmoid))
# vnode.add_op(Dropout(0.1))
vnode.add_op(Dense(1000, tf.nn.relu))
# vnode.add_op(Dense(1000, tf.nn.tanh))
# vnode.add_op(Dense(1000, tf.nn.sigmoid))
# vnode.add_op(Dropout(0.2))
# first node of block
n1 = VariableNode('N1')
add_mlp_ops_to(n1)
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = VariableNode('N2')
add_mlp_ops_to(n2)
# third node of the block
n3 = VariableNode('N3')
add_mlp_ops_to(n3)
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block, (n1, n2, n3)
def create_block(input_node):
def create_mlp_node(name):
# REG_L2 = 1.
# REG_L1 = 1.
n = VariableNode(name)
# n.add_op(Identity())
# n.add_op(Dense(100, tf.nn.relu))
# n.add_op(Dense(100, tf.nn.tanh))
# n.add_op(Dense(100, tf.nn.sigmoid))
# n.add_op(Dropout(0.05))
# n.add_op(Dense(500, tf.nn.relu))
# n.add_op(Dense(500, tf.nn.tanh))
# n.add_op(Dense(500, tf.nn.sigmoid))
# n.add_op(Dropout(0.1))
n.add_op(Dense(1000, tf.nn.relu))
# n.add_op(Dense(1000, tf.nn.tanh))
# n.add_op(Dense(1000, tf.nn.sigmoid))
# n.add_op(Dropout(0.2))
return n
# first node of block
n1 = create_mlp_node('N1')
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = create_mlp_node('N2')
n3 = create_mlp_node('N3')
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block
def create_mlp_block(cell, input_node):
# first node of block
n1 = VariableNode('N1')
create_mlp_node(n1)
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = VariableNode('N2')
create_mlp_node(n2)
n3 = VariableNode('N3')
create_mlp_node(n3)
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block
def create_conv_block(input_nodes):
# first node of block
n1 = Node('N1')
for inpt in input_nodes:
n1.add_op(Connect(cell.graph, inpt, n1))
# second node of block
n2 = Node('N2')
n2.add_op(Conv1D(filter_size=5, num_filters=2))
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_edge(n1, n2)
return block
def create_cell_1(input_nodes):
"""Create a cell with convolution.
Args:
input_nodes (list(Node)): a list of input_nodes for this cell.
Returns:
Cell: the corresponding cell.
"""
cell = Cell(input_nodes)
def create_block(input_node):
def add_mlp_ops_to(vnode):
# REG_L1 = 1.
# REG_L2 = 1.
vnode.add_op(Identity())
vnode.add_op(Dense(100, tf.nn.relu))
vnode.add_op(Dense(100, tf.nn.tanh))
vnode.add_op(Dense(100, tf.nn.sigmoid))
vnode.add_op(Dropout(0.05))
vnode.add_op(Dense(500, tf.nn.relu))
vnode.add_op(Dense(500, tf.nn.tanh))
vnode.add_op(Dense(500, tf.nn.sigmoid))
vnode.add_op(Dropout(0.1))
vnode.add_op(Dense(1000, tf.nn.relu))
vnode.add_op(Dense(1000, tf.nn.tanh))
vnode.add_op(Dense(1000, tf.nn.sigmoid))
vnode.add_op(Dropout(0.2))
# first node of block
n1 = VariableNode('N1')
add_mlp_ops_to(n1)
cell.graph.add_edge(input_node, n1) # fixed input of current block
# second node of block
n2 = VariableNode('N2')
add_mlp_ops_to(n2)
# third node of the block
n3 = VariableNode('N3')
add_mlp_ops_to(n3)
block = Block()
block.add_node(n1)
block.add_node(n2)
block.add_node(n3)
block.add_edge(n1, n2)
block.add_edge(n2, n3)
return block, (n1, n2, n3)
block1, _ = create_block(input_nodes[0])
block2, (vn1, vn2, vn3) = create_block(input_nodes[1])
# first node of block
m_vn1 = MirrorNode(node=vn1)
cell.graph.add_edge(input_nodes[2], m_vn1) # fixed input of current block
# second node of block
m_vn2 = MirrorNode(node=vn2)
# third node of the block
m_vn3 = MirrorNode(node=vn3)
block3 = Block()
block3.add_node(m_vn1)
block3.add_node(m_vn2)
block3.add_node(m_vn3)
block3.add_edge(m_vn1, m_vn2)
block3.add_edge(m_vn2, m_vn3)
cell.add_block(block1)
cell.add_block(block2)
cell.add_block(block3)
cell.set_outputs()
return cell
