def test_create_more_nodes(self):
from deephyper.nas.space import AutoKSearchSpace
from deephyper.nas.space.node import VariableNode
from deephyper.nas.space.op.op1d import Dense
struct = AutoKSearchSpace((5, ), (1, ), regression=True)
vnode1 = VariableNode()
struct.connect(struct.input_nodes[0], vnode1)
vnode1.add_op(Dense(10))
vnode2 = VariableNode()
vnode2.add_op(Dense(10))
struct.connect(vnode1, vnode2)
struct.set_ops([0, 0])
falias = "test_auto_keras_search_spaceure"
struct.draw_graphviz(f"{falias}.dot")
model = struct.create_model()
from tensorflow.keras.utils import plot_model
plot_model(model, to_file=f"{falias}.png", show_shapes=True)
def test_mirror_node():
vnode = VariableNode()
vop = Dense(10)
vnode.add_op(vop)
vnode.add_op(Dense(20))
mnode = MirrorNode(vnode)
vnode.set_op(0)
assert vnode.op == vop
assert mnode.op == vop
def add_mlp_op_(node):
node.add_op(Dense(100, tf.nn.relu))
node.add_op(Dense(100, tf.nn.tanh))
node.add_op(Dense(100, tf.nn.sigmoid))
node.add_op(Dense(500, tf.nn.relu))
node.add_op(Dense(500, tf.nn.tanh))
node.add_op(Dense(500, tf.nn.sigmoid))
node.add_op(Dense(1000, tf.nn.relu))
node.add_op(Dense(1000, tf.nn.tanh))
node.add_op(Dense(1000, tf.nn.sigmoid))
def test_mime_node():
vnode = VariableNode()
vop = Dense(10)
vnode.add_op(vop)
vnode.add_op(Dense(20))
mnode = MimeNode(vnode)
mop = Dense(30)
mnode.add_op(mop)
mnode.add_op(Dense(40))
vnode.set_op(0)
assert vnode.op == vop
assert mnode.op == mop
def build(
self,
input_shape,
output_shape,
regression=True,
num_units=(1, 11),
num_layers=10,
**kwargs
):
"""
Args:
input_shape (tuple, optional): True shape of inputs (no batch size dimension). Defaults to (2,).
output_shape (tuple, optional): True shape of outputs (no batch size dimension).. Defaults to (1,).
num_layers (int, optional): Maximum number of layers to have. Defaults to 10.
num_units (tuple, optional): Range of number of units such as range(start, end, step_size). Defaults to (1, 11).
regression (bool, optional): A boolean defining if the model is a regressor or a classifier. Defaults to True.
Returns:
AutoKSearchSpace: A search space object based on tf.keras implementations.
"""
ss = AutoKSearchSpace(input_shape, output_shape, regression=regression)
prev_node = ss.input_nodes[0]
for _ in range(num_layers):
vnode = VariableNode()
vnode.add_op(Identity())
for i in range(*num_units):
vnode.add_op(Dense(i, tf.nn.relu))
ss.connect(prev_node, vnode)
prev_node = vnode
return ss
def add_dense_to_(node):
node.add_op(Identity()) # we do not want to create a layer in this case
activations = [None, swish, tf.nn.relu, tf.nn.tanh, tf.nn.sigmoid]
for units in range(16, 97, 16):
for activation in activations:
node.add_op(Dense(units=units, activation=activation))
def build(self,
input_shape,
output_shape,
units=[128, 64, 32, 16, 8, 16, 32, 64, 128],
num_layers=5,
**kwargs):
ss = KSearchSpace(input_shape, output_shape)
inp = ss.input_nodes[0]
# auto-encoder
units = [128, 64, 32, 16, 8, 16, 32, 64, 128]
prev_node = inp
d = 1
for i in range(len(units)):
vnode = VariableNode()
vnode.add_op(Identity())
if d == 1 and units[i] < units[i + 1]:
d = -1
for u in range(min(2, units[i]), max(2, units[i]) + 1, 2):
vnode.add_op(Dense(u, tf.nn.relu))
latente_space = vnode
else:
for u in range(min(units[i], units[i + d]),
max(units[i], units[i + d]) + 1, 2):
vnode.add_op(Dense(u, tf.nn.relu))
ss.connect(prev_node, vnode)
prev_node = vnode
out2 = ConstantNode(op=Dense(output_shape[0][0], name="output_0"))
ss.connect(prev_node, out2)
# regressor
prev_node = latente_space
# prev_node = inp
for _ in range(num_layers):
vnode = VariableNode()
for i in range(16, 129, 16):
vnode.add_op(Dense(i, tf.nn.relu))
ss.connect(prev_node, vnode)
prev_node = vnode
out1 = ConstantNode(op=Dense(output_shape[1][0], name="output_1"))
ss.connect(prev_node, out1)
return ss
def create_search_space(
input_shape=(32, 32, 3),
output_shape=(10, ),
num_filters=8,
num_blocks=4,
normal_cells=2,
reduction_cells=1,
repetitions=3,
*args,
**kwargs,
):
ss = AutoKSearchSpace(input_shape, output_shape, regression=False)
source = prev_input = ss.input_nodes[0]
# look over skip connections within a range of the 3 previous nodes
hidden_states = collections.deque([source, source], maxlen=2)
for ri in range(repetitions):
for nci in range(normal_cells):
# generate a normal cell
cout = generate_cell(
ss,
hidden_states,
num_blocks,
strides=1,
mime=ri + nci > 0,
num_filters=num_filters,
)
hidden_states.append(cout)
if ri < repetitions - 1: # we don't want the last cell to be a reduction cell
for rci in range(reduction_cells):
# generate a reduction cell
cout = generate_cell(
ss,
hidden_states,
num_blocks,
strides=2,
mime=ri + rci > 0,
num_filters=num_filters,
)
hidden_states.append(cout)
# out_node = ConstantNode(op=Dense(100, activation=tf.nn.relu))
out_dense = VariableNode()
out_dense.add_op(Identity())
for units in [10, 20, 50, 100, 200, 500, 1000]:
out_dense.add_op(Dense(units, activation=tf.nn.relu))
ss.connect(cout, out_dense)
out_dropout = VariableNode()
out_dropout.add_op(Identity())
for drop_rate in [0.01, 0.02, 0.05, 0.1, 0.2, 0.5, 0.8]:
out_dropout.add_op(Dropout(rate=drop_rate))
ss.connect(out_dense, out_dropout)
return ss
def add_dense_op_(node):
# node.add_op(Identity())
node.add_op(Dense(units=10))
node.add_op(Dense(units=50))
node.add_op(Dense(units=100))
node.add_op(Dense(units=200))
node.add_op(Dense(units=250))
node.add_op(Dense(units=500))
node.add_op(Dense(units=750))
node.add_op(Dense(units=1000))
def add_mlp_op_(node):
node.add_op(Identity())
node.add_op(Dense(100, tf.nn.relu))
node.add_op(Dense(100, tf.nn.tanh))
node.add_op(Dense(100, tf.nn.sigmoid))
node.add_op(Dropout(0.3))
node.add_op(Dense(500, tf.nn.relu))
node.add_op(Dense(500, tf.nn.tanh))
node.add_op(Dense(500, tf.nn.sigmoid))
node.add_op(Dropout(0.4))
node.add_op(Dense(1000, tf.nn.relu))
node.add_op(Dense(1000, tf.nn.tanh))
node.add_op(Dense(1000, tf.nn.sigmoid))
node.add_op(Dropout(0.5))
def create_structure(input_shape=(2,), output_shape=(1,), *args, **kwargs):
struct = AutoKSearchSpace(input_shape, output_shape, regression=False)
n1 = ConstantNode(op=Conv1D(filter_size=20, num_filters=128), name='N')
struct.connect(struct.input_nodes[0], n1)
n2 = ConstantNode(op=Activation(activation='relu'), name='N')
struct.connect(n1, n2)
n3 = ConstantNode(op=MaxPooling1D(pool_size=1, padding='same'), name='N')
struct.connect(n2, n3)
n4 = ConstantNode(op=Conv1D(filter_size=10, num_filters=128),name='N')
struct.connect(n3, n4)
n5 = ConstantNode(op=Activation(activation='relu'), name='N')
struct.connect(n4, n5)
n6 = ConstantNode(op=MaxPooling1D(pool_size=10, padding='same'), name='N')
struct.connect(n5, n6)
n7 = ConstantNode(op=Flatten(), name='N')
struct.connect(n6, n7)
n8 = ConstantNode(op=Dense(units=200), name='N')
struct.connect(n7, n8)
n9 = ConstantNode(op=Activation(activation='relu'), name='N')
struct.connect(n8, n9)
n10 = ConstantNode(op=Dropout(rate=0.1), name='N')
struct.connect(n9, n10)
n11 = ConstantNode(op=Dense(units=20), name='N')
struct.connect(n10, n11)
n12 = ConstantNode(op=Activation(activation='relu'), name='N')
struct.connect(n11, n12)
n13 = ConstantNode(op=Dropout(rate=0.1), name='N')
struct.connect(n12, n13)
return struct
def create_structure(input_shape=[(1, ), (942, ), (5270, ), (2048, )],
output_shape=(1, ),
num_cells=2,
*args,
**kwargs):
struct = AutoKSearchSpace(input_shape, output_shape, regression=True)
input_nodes = struct.input_nodes
output_submodels = [input_nodes[0]]
for i in range(1, 4):
cnode1 = ConstantNode(name='N', op=Dense(1000, tf.nn.relu))
struct.connect(input_nodes[i], cnode1)
cnode2 = ConstantNode(name='N', op=Dense(1000, tf.nn.relu))
struct.connect(cnode1, cnode2)
vnode1 = VariableNode(name='N3')
add_mlp_op_(vnode1)
struct.connect(cnode2, vnode1)
output_submodels.append(vnode1)
merge1 = ConstantNode(name='Merge')
# merge1.set_op(Concatenate(struct, merge1, output_submodels))
merge1.set_op(Concatenate(struct, output_submodels))
cnode4 = ConstantNode(name='N', op=Dense(1000, tf.nn.relu))
struct.connect(merge1, cnode4)
prev = cnode4
for i in range(num_cells):
cnode = ConstantNode(name='N', op=Dense(1000, tf.nn.relu))
struct.connect(prev, cnode)
merge = ConstantNode(name='Merge')
# merge.set_op(AddByPadding(struct, merge, [cnode, prev]))
merge.set_op(AddByPadding(struct, [cnode, prev]))
prev = merge
return struct
def test_create_one_vnode_with_wrong_output_shape(self):
from deephyper.nas.space import KSearchSpace
struct = KSearchSpace((5, ), (1, ))
from deephyper.nas.space.node import VariableNode
vnode = VariableNode()
struct.connect(struct.input_nodes[0], vnode)
from deephyper.nas.space.op.op1d import Dense
vnode.add_op(Dense(10))
struct.set_ops([0])
with pytest.raises(WrongOutputShape):
struct.create_model()
def test_create_multiple_inputs_with_one_vnode(self):
from deephyper.nas.space import KSearchSpace
from deephyper.nas.space.node import VariableNode, ConstantNode
from deephyper.nas.space.op.op1d import Dense
from deephyper.nas.space.op.merge import Concatenate
struct = KSearchSpace([(5, ), (5, )], (1, ))
merge = ConstantNode()
merge.set_op(Concatenate(struct, struct.input_nodes))
vnode1 = VariableNode()
struct.connect(merge, vnode1)
vnode1.add_op(Dense(1))
struct.set_ops([0])
struct.create_model()
def create_search_space(
input_shape=(11937, ), output_shape=(86, ), num_layers=10, *args,
**kwargs):
# print("input_shape:", input_shape, ", output_shape:", output_shape,", num_layers:", num_layers)
arch = KSearchSpace(input_shape, output_shape)
source = prev_input = arch.input_nodes[0]
# look over skip connections within a range of the 3 previous nodes
anchor_points = collections.deque([source], maxlen=3)
for _ in range(num_layers):
vnode = VariableNode()
add_dense_to_(vnode)
arch.connect(prev_input, vnode)
# * Cell output
cell_output = vnode
cmerge = ConstantNode()
cmerge.set_op(AddByProjecting(arch, [cell_output], activation='relu'))
for anchor in anchor_points:
skipco = VariableNode()
skipco.add_op(Tensor([]))
skipco.add_op(Connect(arch, anchor))
arch.connect(skipco, cmerge)
# ! for next iter
prev_input = cmerge
anchor_points.append(prev_input)
cout = ConstantNode(op=Dense(86, activation="sigmoid"))
arch.connect(prev_input, cout)
return arch
def test_create_one_vnode(self):
from deephyper.nas.space import KSearchSpace
struct = KSearchSpace((5, ), (1, ))
from deephyper.nas.space.node import VariableNode
vnode = VariableNode()
struct.connect(struct.input_nodes[0], vnode)
from deephyper.nas.space.op.op1d import Dense
vnode.add_op(Dense(1))
struct.set_ops([0])
falias = "test_keras_search_spaceure"
struct.draw_graphviz(f"{falias}.dot")
model = struct.create_model()
from tensorflow.keras.utils import plot_model
plot_model(model, to_file=f"{falias}.png", show_shapes=True)
def gen_vnode(self) -> VariableNode:
vnode = VariableNode()
for i in range(1, 11):
vnode.add_op(Dense(i, tf.nn.relu))
return vnode
