def test_config(make_model):
# Disable the redefined-outer-name violation in this function
# pylint: disable=redefined-outer-name
model = make_model
expected_num_parameters = model.layers[0].count_params()
# Serialize model and use config to create new layer
model_config = model.get_config()
layer_config = model_config['layers'][0]['config']
if 'mpo' in model.layers[0].name:
new_model = DenseMPO.from_config(layer_config)
elif 'decomp' in model.layers[0].name:
new_model = DenseDecomp.from_config(layer_config)
elif 'condenser' in model.layers[0].name:
new_model = DenseCondenser.from_config(layer_config)
elif 'expander' in model.layers[0].name:
new_model = DenseExpander.from_config(layer_config)
elif 'entangler' in model.layers[0].name:
new_model = DenseEntangler.from_config(layer_config)
# Build the layer so we can count params below
new_model.build(layer_config['batch_input_shape'])
# Check that original layer had same num params as layer built from config
np.testing.assert_equal(expected_num_parameters, new_model.count_params())
def test_entangler_asymmetric_num_parameters_output_shape(
num_legs, num_levels, leg_dims):
leg_dim, out_leg_dim = leg_dims
data_shape = (leg_dim**num_legs, )
model = Sequential()
model.add(
DenseEntangler(out_leg_dim**num_legs,
num_legs=num_legs,
num_levels=num_levels,
use_bias=True,
activation='relu',
input_shape=data_shape))
primary = leg_dim
secondary = out_leg_dim
if leg_dim > out_leg_dim:
primary, secondary = secondary, primary
expected_num_parameters = (num_levels - 1) * (num_legs - 1) * (
primary**4
) + (num_legs - 2) * primary**3 * secondary + primary**2 * secondary**2 + (
out_leg_dim**num_legs)
np.testing.assert_equal(expected_num_parameters, model.count_params())
data = np.random.randint(10, size=(10, data_shape[0]))
out = model(data)
np.testing.assert_equal(out.shape, (data.shape[0], out_leg_dim**num_legs))
def make_model(dummy_data, request):
# Disable the redefined-outer-name violation in this function
# pylint: disable=redefined-outer-name
data, _ = dummy_data
if request.param == 'DenseMPO':
model = Sequential()
model.add(
DenseMPO(data.shape[1],
num_nodes=int(math.log(int(data.shape[1]), 8)),
bond_dim=8,
use_bias=True,
activation='relu',
input_shape=(data.shape[1],)))
model.add(Dense(1, activation='sigmoid'))
elif request.param == 'DenseDecomp':
model = Sequential()
model.add(
DenseDecomp(512,
decomp_size=128,
use_bias=True,
activation='relu',
input_shape=(data.shape[1],)))
model.add(Dense(1, activation='sigmoid'))
elif request.param == 'DenseCondenser':
model = Sequential()
model.add(
DenseCondenser(exp_base=2,
num_nodes=3,
use_bias=True,
activation='relu',
input_shape=(data.shape[1],)))
model.add(Dense(1, activation='sigmoid'))
elif request.param == 'DenseExpander':
model = Sequential()
model.add(
DenseExpander(exp_base=2,
num_nodes=3,
use_bias=True,
activation='relu',
input_shape=(data.shape[-1],)))
model.add(Dense(1, activation='sigmoid'))
elif request.param == 'DenseEntangler':
num_legs = 3
leg_dim = round(data.shape[-1]**(1. / num_legs))
assert leg_dim**num_legs == data.shape[-1]
model = Sequential()
model.add(
DenseEntangler(leg_dim**num_legs,
num_legs=num_legs,
num_levels=3,
use_bias=True,
activation='relu',
input_shape=(data.shape[1],)))
model.add(Dense(1, activation='sigmoid'))
return model
def test_entangler_num_parameters(dummy_data):
# Disable the redefined-outer-name violation in this function
# pylint: disable=redefined-outer-name
data, _ = dummy_data
num_legs = 3
num_levels = 3
leg_dim = round(data.shape[-1]**(1. / num_legs))
assert leg_dim**num_legs == data.shape[-1]
model = Sequential()
model.add(
DenseEntangler(leg_dim**num_legs,
num_legs=num_legs,
num_levels=num_levels,
use_bias=True,
activation='relu',
input_shape=(data.shape[1],)))
# num_params = entangler_node_params + bias_params
expected_num_parameters = num_levels * (leg_dim**4) + leg_dim**num_legs
np.testing.assert_equal(expected_num_parameters, model.count_params())