def optimizer(self, optimizer: Optional[Optimizer] = None) -> None:
"""
Set optimizer.
Args:
optimizer (Optimizer): optimizer to use with the generator.
Raises:
AquaError: invalid input.
"""
if optimizer:
if isinstance(optimizer, Optimizer):
self._optimizer = optimizer
else:
raise AquaError('Please provide an Optimizer object to use'
'as the generator optimizer.')
else:
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=self._snapshot_dir)
def train1(self, train_params, batch_size, verb=True):
alpha, gamma, epsilon = train_params
self.episode += 1
state = self.environment.reset()
total_reward = 0
loss_list = []
# sample from policy
done = False
while not done:
a = self.sample_action(state, [epsilon])
new_state, r, done, = self.environment.step(a)
total_reward += r
self.D.pop(0)
self.D.append((state, a, r, new_state, done))
mB_ind = np.random.choice(range(self.memory_size), size=batch_size, replace=True)
mB = np.array(self.D)[mB_ind]
t = []
for j in range(batch_size):
y_j = mB[j][2] * mB[j][-1] or mB[j][2] + gamma * max(self.get_qvalues([mB[j][3]], self.target_theta)[0])
t.append([y_j, mB[j][0], mB[j][1]])
t = np.array(t)
adam = ADAM(maxiter=10, amsgrad=True, lr=alpha)
if self.debug:
start = datetime.now()
self.theta, batch_losses, _ = adam.optimize(len(self.theta), lambda x: self.loss(x, t), initial_point=self.theta)
#gradient_function=lambda x: self.gradient(x, t)
loss_list.append(batch_losses)
if self.debug:
print(datetime.now() - start)
if self.train_counter % self.configuration.target_replacement == 0:
self.target_theta = copy.deepcopy(self.theta.copy())
self.train_counter = self.train_counter + 1
# update state
state = new_state
self.loss_mem.append(np.mean(np.array(loss_list).flatten()))
if verb:
print('train it:', self.episode, ' Return: ', total_reward, ' Loss: ', self.loss_mem[-1],
' epsilon ', epsilon)
return total_reward
def __init__(self, n_features: int = 1, n_out: int = 1) -> None:
"""
Args:
n_features: Dimension of input data vector.
n_out: Dimension of the discriminator's output vector.
"""
super().__init__()
self._n_features = n_features
self._n_out = n_out
self._discriminator = DiscriminatorNet(self._n_features, self._n_out)
self._optimizer = ADAM(maxiter=1, tol=1e-6, lr=1e-3, beta_1=0.7, beta_2=0.99,
noise_factor=1e-4,
eps=1e-6, amsgrad=True)
self._ret = {}
def make_opt(opt_str):
if opt_str == "spsa":
optimizer = SPSA(max_trials=100, save_steps=1, c0=4.0, skip_calibration=True)
elif opt_str == "cobyla":
optimizer = COBYLA(maxiter=1000, disp=False, rhobeg=1.0, tol=None)
elif opt_str == "adam":
optimizer = ADAM(maxiter=10000, tol=1e-6, lr=1e-3, beta_1=0.9, beta_2=0.99, noise_factor=1e-8, eps=1e-10)
else:
print('error in building OPTIMIZER: {} IT DOES NOT EXIST'.format(opt_str))
sys.exit(1)
return optimizer
def minimize(self, cost_function, initial_params=None):
"""
Minimizes given cost function using optimizers from Qiskit Aqua.
Args:
cost_function(): python method which takes numpy.ndarray as input
initial_params(np.ndarray): initial parameters to be used for optimization
Returns:
optimization_results(scipy.optimize.OptimizeResults): results of the optimization.
"""
history = []
if self.method == "SPSA":
optimizer = SPSA(**self.options)
elif self.method == "ADAM" or self.method == "AMSGRAD":
if self.method == "AMSGRAD":
self.options["amsgrad"] = True
optimizer = ADAM(**self.options)
number_of_variables = len(initial_params)
if self.keep_value_history:
cost_function_wrapper = recorder(cost_function)
else:
cost_function_wrapper = _CostFunctionWrapper(cost_function)
gradient_function = None
if hasattr(cost_function, "gradient") and callable(
getattr(cost_function, "gradient")):
gradient_function = cost_function.gradient
solution, value, nit = optimizer.optimize(
num_vars=number_of_variables,
objective_function=cost_function_wrapper,
initial_point=initial_params,
gradient_function=gradient_function,
)
if self.keep_value_history:
nfev = len(cost_function_wrapper.history)
history = cost_function_wrapper.history
else:
nfev = cost_function_wrapper.number_of_calls
history = []
return optimization_result(
opt_value=value,
opt_params=solution,
nit=nit,
history=history,
nfev=nfev,
)
def train1(self, train_params, batch_size):
alpha, gamma, epsilon = train_params
s = self.environment.reset()
done = False
total_reward = 0
while not done:
a = self.sample_action(s, [epsilon])
s1, r, done, = self.environment.step(a)
total_reward += r
self.D.pop(0)
self.D.append((s, a, r, s1, done))
mB_ind = np.random.choice(range(self.memory_size),
size=batch_size,
replace=False)
mB = np.array(self.D)[mB_ind]
t = []
for j in range(batch_size):
if mB[j][-1]:
y_j = mB[j][2]
else:
y_j = mB[j][2] + gamma * max(
self.get_qvalues([mB[j][3]], self.theta)[0])
y_j /= 2
y_j += 0.5
t.append([y_j, mB[j][0], mB[j][1]])
t = np.array(t)
adam = ADAM(maxiter=10, lr=alpha)
if self.debug:
start = datetime.now()
theta, _, _ = adam.optimize(3 * self.nb_qbits,
lambda x: self.loss(x, t),
initial_point=self.theta)
if self.debug:
print(datetime.now() - start)
return total_reward
class NumpyDiscriminator(DiscriminativeNetwork):
"""
Discriminator
"""
CONFIGURATION = {
'name': 'NumpyDiscriminator',
'description': 'qGAN Discriminator Network',
'input_schema': {
'$schema': 'http://json-schema.org/schema#',
'id': 'discriminator_schema',
'type': 'object',
'properties': {
'n_features': {
'type': 'integer',
'default': 1
},
'n_out': {
'type': 'integer',
'default': 1
}
},
'additionalProperties': False
}
}
def __init__(self, n_features=1, n_out=1):
"""
Initialize the discriminator.
Args:
n_features: int, Dimension of input data vector.
n_out: int, Dimension of the discriminator's output vector.
"""
self._n_features = n_features
self._n_out = n_out
self._discriminator = DiscriminatorNet(self._n_features, self._n_out)
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-5,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-4,
eps=1e-6,
amsgrad=True)
self._ret = {}
@classmethod
def get_section_key_name(cls):
return Pluggable.SECTION_KEY_DISCRIMINATIVE_NETWORK
@staticmethod
def check_pluggable_valid():
return
def set_seed(self, seed):
"""
Set seed.
Args:
seed: int, seed
Returns:
"""
np.random.RandomState(seed)
return
def save_model(self, snapshot_dir):
"""
Save discriminator model
Args:
snapshot_dir: str, directory path for saving the model
Returns:
"""
# save self._discriminator.params_values
np.save(
os.path.join(snapshot_dir, 'np_discriminator_architecture.csv'),
self._discriminator.architecture)
np.save(os.path.join(snapshot_dir, 'np_discriminator_memory.csv'),
self._discriminator.memory)
np.save(os.path.join(snapshot_dir, 'np_discriminator_params.csv'),
self._discriminator.parameters)
self._optimizer.save_params(snapshot_dir)
return
def load_model(self, load_dir):
"""
Save discriminator model
Args:
dir: str, file with stored pytorch discriminator model to be loaded
Returns:
"""
self._discriminator.architecture = np.load(
os.path.join(load_dir, 'np_discriminator_architecture.csv'))
self._discriminator.memory = np.load(
os.path.join(load_dir, 'np_discriminator_memory.csv'))
self._discriminator.parameters = np.load(
os.path.join(load_dir, 'np_discriminator_params.csv'))
self._optimizer.load_params(load_dir)
return
def get_discriminator(self):
"""
Get discriminator
Returns: discriminator object
"""
return self._discriminator
def get_label(self, x, detach=False):
"""
Get data sample labels, i.e. true or fake.
Args:
x: numpy array, Discriminator input, i.e. data sample.
detach: depreciated for numpy network
Returns: numpy array, Discriminator output, i.e. data label
"""
return self._discriminator.forward(x)
def loss(self, x, y, weights=None):
"""
Loss function
Args:
x: array, sample label (equivalent to discriminator output)
y: array, target label
weights: array, customized scaling for each sample (optional)
Returns: float, loss function
"""
if weights is not None:
# Use weights as scaling factors for the samples and compute the sum
return (-1) * np.dot(
np.multiply(
y, np.log(np.maximum(np.ones(np.shape(x)) * 1e-4, x))) +
np.multiply(
np.ones(np.shape(y)) - y,
np.log(
np.maximum(
np.ones(np.shape(x)) * 1e-4,
np.ones(np.shape(x)) - x))), weights)
else:
# Compute the mean
return (-1) * np.mean(
np.multiply(
y, np.log(np.maximum(np.ones(np.shape(x)) * 1e-4, x))) +
np.multiply(
np.ones(np.shape(y)) - y,
np.log(
np.maximum(
np.ones(np.shape(x)) * 1e-4,
np.ones(np.shape(x)) - x))))
def _get_objective_function(self, data, weights):
"""
Get the objective function
Args:
data: training and generated data
weights: weights corresponding to training resp. generated data
Returns: objective function for the optimization
"""
real_batch = data[0]
real_prob = weights[0]
generated_batch = data[1]
generated_prob = weights[1]
def objective_function(params):
self._discriminator.parameters = params
# Train on Real Data
prediction_real = self.get_label(real_batch)
loss_real = self.loss(prediction_real,
np.ones(np.shape(prediction_real)),
real_prob)
prediction_fake = self.get_label(generated_batch)
loss_fake = self.loss(prediction_fake,
np.zeros(np.shape(prediction_fake)),
generated_prob)
return 0.5 * (loss_real[0] + loss_fake[0])
return objective_function
def _get_gradient_function(self, data, weights):
"""
Get the gradient function
Args:
data: training and generated data
weights: weights corresponding to training resp. generated data
Returns: Gradient function for the optimization
"""
real_batch = data[0]
real_prob = weights[0]
generated_batch = data[1]
generated_prob = weights[1]
def gradient_function(params):
self._discriminator.parameters = params
prediction_real = self.get_label(real_batch)
grad_real = self._discriminator.backward(
prediction_real, np.ones(np.shape(prediction_real)), real_prob)
prediction_generated = self.get_label(generated_batch)
grad_generated = self._discriminator.backward(
prediction_generated, np.zeros(np.shape(prediction_generated)),
generated_prob)
return np.add(grad_real, grad_generated)
return gradient_function
def train(self,
data,
weights,
penalty=False,
quantum_instance=None,
shots=None):
"""
Perform one training step w.r.t to the discriminator's parameters
Args:
data: [real_batch, generated_batch]
real_batch: array, Training data batch.
generated_batch: array, Generated data batch.
weights: [real_prob, generated_prob]
penalty: Boolean, Depreciated for classical networks.
quantum_instance: QuantumInstance, Depreciated for classical networks.
shots: int, Number of shots for hardware or qasm execution. Depreciated for classical networks.
Returns: dict, with Discriminator loss and updated parameters.
"""
# Train on Generated Data
self._shots = shots
# Force single optimization iteration
self._optimizer._maxiter = 1
self._optimizer._t = 0
objective = self._get_objective_function(data, weights)
gradient = self._get_gradient_function(data, weights)
self._discriminator.parameters, loss, nfev = \
self._optimizer.optimize(num_vars=len(self._discriminator.parameters), objective_function=objective,
initial_point=np.array(self._discriminator.parameters), gradient_function=gradient)
self._ret['loss'] = loss
self._ret['params'] = self._discriminator.parameters
return self._ret
class NumPyDiscriminator(DiscriminativeNetwork):
"""
Discriminator based on NumPy
"""
def __init__(self, n_features: int = 1, n_out: int = 1) -> None:
"""
Args:
n_features: Dimension of input data vector.
n_out: Dimension of the discriminator's output vector.
"""
super().__init__()
self._n_features = n_features
self._n_out = n_out
self._discriminator = DiscriminatorNet(self._n_features, self._n_out)
self._optimizer = ADAM(maxiter=1, tol=1e-6, lr=1e-3, beta_1=0.7, beta_2=0.99,
noise_factor=1e-4,
eps=1e-6, amsgrad=True)
self._ret = {}
def set_seed(self, seed):
"""
Set seed.
Args:
seed (int): seed
"""
aqua_globals.random_seed = seed
def save_model(self, snapshot_dir):
"""
Save discriminator model
Args:
snapshot_dir (str): directory path for saving the model
"""
# save self._discriminator.params_values
np.save(os.path.join(snapshot_dir, 'np_discriminator_architecture.csv'),
self._discriminator.architecture)
np.save(os.path.join(snapshot_dir,
'np_discriminator_memory.csv'), self._discriminator.memory)
np.save(os.path.join(snapshot_dir,
'np_discriminator_params.csv'), self._discriminator.parameters)
self._optimizer.save_params(snapshot_dir)
def load_model(self, load_dir):
"""
Load discriminator model
Args:
load_dir (str): file with stored pytorch discriminator model to be loaded
"""
self._discriminator.architecture = \
np.load(os.path.join(load_dir, 'np_discriminator_architecture.csv'))
self._discriminator.memory = np.load(os.path.join(load_dir,
'np_discriminator_memory.csv'))
self._discriminator.parameters = np.load(os.path.join(load_dir,
'np_discriminator_params.csv'))
self._optimizer.load_params(load_dir)
@property
def discriminator_net(self):
"""
Get discriminator
Returns:
DiscriminatorNet: discriminator object
"""
return self._discriminator
@discriminator_net.setter
def discriminator_net(self, net):
self._discriminator = net
def get_label(self, x, detach=False): # pylint: disable=arguments-differ,unused-argument
"""
Get data sample labels, i.e. true or fake.
Args:
x (numpy.ndarray): Discriminator input, i.e. data sample.
detach (bool): depreciated for numpy network
Returns:
numpy.ndarray: Discriminator output, i.e. data label
"""
return self._discriminator.forward(x)
def loss(self, x, y, weights=None):
"""
Loss function
Args:
x (numpy.ndarray): sample label (equivalent to discriminator output)
y (numpy.ndarray): target label
weights(numpy.ndarray): customized scaling for each sample (optional)
Returns:
float: loss function
"""
if weights is not None:
# Use weights as scaling factors for the samples and compute the sum
return (-1) * np.dot(np.multiply(y,
np.log(np.maximum(np.ones(np.shape(x)) * 1e-4, x)))
+ np.multiply(np.ones(np.shape(y)) - y,
np.log(np.maximum(np.ones(np.shape(x)) * 1e-4,
np.ones(np.shape(x)) - x))),
weights)
else:
# Compute the mean
return (-1) * np.mean(np.multiply(y,
np.log(np.maximum(np.ones(np.shape(x)) * 1e-4, x)))
+ np.multiply(np.ones(np.shape(y)) - y,
np.log(np.maximum(np.ones(np.shape(x)) * 1e-4,
np.ones(np.shape(x)) - x))))
def _get_objective_function(self, data, weights):
"""
Get the objective function
Args:
data (tuple): training and generated data
weights (numpy.ndarray): weights corresponding to training resp. generated data
Returns:
objective_function: objective function for the optimization
"""
real_batch = data[0]
real_prob = weights[0]
generated_batch = data[1]
generated_prob = weights[1]
def objective_function(params):
self._discriminator.parameters = params
# Train on Real Data
prediction_real = self.get_label(real_batch)
loss_real = self.loss(prediction_real, np.ones(np.shape(prediction_real)), real_prob)
prediction_fake = self.get_label(generated_batch)
loss_fake = self.loss(prediction_fake,
np.zeros(np.shape(prediction_fake)), generated_prob)
return 0.5 * (loss_real[0] + loss_fake[0])
return objective_function
def _get_gradient_function(self, data, weights):
"""
Get the gradient function
Args:
data (tuple): training and generated data
weights (numpy.ndarray): weights corresponding to training resp. generated data
Returns:
gradient_function: Gradient function for the optimization
"""
real_batch = data[0]
real_prob = weights[0]
generated_batch = data[1]
generated_prob = weights[1]
def gradient_function(params):
self._discriminator.parameters = params
prediction_real = self.get_label(real_batch)
grad_real = self._discriminator.backward(prediction_real,
np.ones(np.shape(prediction_real)), real_prob)
prediction_generated = self.get_label(generated_batch)
grad_generated = self._discriminator.backward(prediction_generated, np.zeros(
np.shape(prediction_generated)), generated_prob)
return np.add(grad_real, grad_generated)
return gradient_function
def train(self, data, weights, penalty=False, quantum_instance=None, shots=None):
"""
Perform one training step w.r.t to the discriminator's parameters
Args:
data (tuple(numpy.ndarray, numpy.ndarray)):
real_batch: array, Training data batch.
generated_batch: array, Generated data batch.
weights (tuple):real problem, generated problem
penalty (bool): Depreciated for classical networks.
quantum_instance (QuantumInstance): Depreciated for classical networks.
shots (int): Number of shots for hardware or qasm execution.
Ignored for classical networks.
Returns:
dict: with Discriminator loss and updated parameters.
"""
# Train on Generated Data
# Force single optimization iteration
self._optimizer._maxiter = 1
self._optimizer._t = 0
objective = self._get_objective_function(data, weights)
gradient = self._get_gradient_function(data, weights)
self._discriminator.parameters, loss, _ = \
self._optimizer.optimize(num_vars=len(self._discriminator.parameters),
objective_function=objective,
initial_point=np.array(self._discriminator.parameters),
gradient_function=gradient)
self._ret['loss'] = loss
self._ret['params'] = self._discriminator.parameters
return self._ret
class QuantumGenerator(GenerativeNetwork):
"""Quantum Generator.
The quantum generator is a parametrized quantum circuit which can be trained with the
:class:`~qiskit.aqua.algorithms.QGAN` algorithm
to generate a quantum state which approximates the probability
distribution of given training data. At the beginning of the training the parameters will
be set randomly, thus, the output will is random. Throughout the training the quantum
generator learns to represent the target distribution.
Eventually, the trained generator can be used for state preparation e.g. in QAE.
"""
def __init__(self,
bounds: np.ndarray,
num_qubits: Union[List[int], np.ndarray],
generator_circuit: Optional[
Union[UnivariateVariationalDistribution,
MultivariateVariationalDistribution,
QuantumCircuit]] = None,
init_params: Optional[Union[List[float], np.ndarray]] = None,
optimizer: Optional[Optimizer] = None,
gradient_function: Optional[Union[Callable, Gradient]] = None,
snapshot_dir: Optional[str] = None) -> None:
"""
Args:
bounds: k min/max data values [[min_1,max_1],...,[min_k,max_k]],
given input data dim k
num_qubits: k numbers of qubits to determine representation resolution,
i.e. n qubits enable the representation of 2**n values [n_1,..., n_k]
generator_circuit: a UnivariateVariationalDistribution for univariate data,
a MultivariateVariationalDistribution for multivariate data,
or a QuantumCircuit implementing the generator.
init_params: 1D numpy array or list, Initialization for
the generator's parameters.
optimizer: optimizer to be used for the training of the generator
gradient_function: A Gradient object, or a function returning partial
derivatives of the loss function w.r.t. the generator variational
params.
snapshot_dir: str or None, if not None save the optimizer's parameter after every
update step to the given directory
Raises:
AquaError: Set multivariate variational distribution to represent multivariate data
"""
super().__init__()
self._bounds = bounds
self._num_qubits = num_qubits
self.generator_circuit = generator_circuit
if generator_circuit is None:
circuit = QuantumCircuit(sum(num_qubits))
circuit.h(circuit.qubits)
var_form = TwoLocal(sum(num_qubits),
'ry',
'cz',
reps=1,
entanglement='circular')
circuit.compose(var_form, inplace=True)
# Set generator circuit
self.generator_circuit = circuit
if isinstance(generator_circuit,
(UnivariateVariationalDistribution,
MultivariateVariationalDistribution)):
warnings.warn(
'Passing a UnivariateVariationalDistribution or MultivariateVariational'
'Distribution as ``generator_circuit`` is deprecated as of Aqua 0.8.0 '
'and the support will be removed no earlier than 3 months after the '
'release date. You should pass a QuantumCircuit instead.',
DeprecationWarning,
stacklevel=2)
self._free_parameters = generator_circuit._var_form_params
self.generator_circuit = generator_circuit._var_form
else:
self._free_parameters = sorted(self.generator_circuit.parameters,
key=lambda p: p.name)
if init_params is None:
init_params = aqua_globals.random.random(
self.generator_circuit.num_parameters) * 2e-2
self._bound_parameters = init_params
# Set optimizer for updating the generator network
self._snapshot_dir = snapshot_dir
self.optimizer = optimizer
self._gradient_function = gradient_function
if np.ndim(self._bounds) == 1:
bounds = np.reshape(self._bounds, (1, len(self._bounds)))
else:
bounds = self._bounds
for j, prec in enumerate(self._num_qubits):
# prepare data grid for dim j
grid = np.linspace(bounds[j, 0], bounds[j, 1], (2**prec))
if j == 0:
if len(self._num_qubits) > 1:
self._data_grid = [grid]
else:
self._data_grid = grid # type: ignore
self._grid_elements = grid
elif j == 1:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = [g_e]
temp0.append(g)
temp.append(temp0)
self._grid_elements = temp # type: ignore
else:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = deepcopy(g_e)
temp0.append(g)
temp.append(temp0)
self._grid_elements = deepcopy(temp) # type: ignore
self._data_grid = np.array(self._data_grid) # type: ignore
self._seed = 7
self._shots = None
self._discriminator = None
self._ret = {} # type: Dict[str, Any]
@property
def parameter_values(self) -> Union[List, np.ndarray]:
"""
Get parameter values from the quantum generator
Returns:
Current parameter values
"""
return self._bound_parameters
@parameter_values.setter
def parameter_values(self, p_values: Union[List, np.ndarray]) -> None:
"""
Set parameter values for the quantum generator
Args:
p_values: Parameter values
"""
self._bound_parameters = p_values
@property
def seed(self) -> int:
"""
Get seed.
"""
return self._seed
@seed.setter
def seed(self, seed: int) -> None:
"""
Set seed.
Args:
seed (int): seed to use.
"""
self._seed = seed
aqua_globals.random_seed = seed
def set_seed(self, seed: int) -> None:
"""
Set seed.
Args:
seed (int): seed
"""
warnings.warn(
'Using set_seed() is deprecated as of Aqua 0.9.0 '
'and support for it will be removed no earlier than '
'three months after the release date. Please use '
'the QuantumGenerator.seed property instead.',
DeprecationWarning,
stacklevel=2)
aqua_globals.random_seed = seed
@property
def discriminator(self) -> DiscriminativeNetwork:
"""
Get discriminator.
"""
return self._discriminator
@discriminator.setter
def discriminator(self, discriminator: DiscriminativeNetwork) -> None:
"""
Set discriminator.
Args:
discriminator (DiscriminativeNetwork): Discriminator used to
compute the loss function.
"""
self._discriminator = discriminator
def set_discriminator(self, discriminator: DiscriminativeNetwork) -> None:
"""
Set discriminator network.
Args:
discriminator (DiscriminativeNetwork): Discriminator used to
compute the loss function.
"""
warnings.warn(
'Using set_discriminator() is deprecated as of '
'Aqua 0.9.0 and support for it will be removed no earlier'
' than three months after the release date. Please use '
'the QuantumGenerator.discriminator property instead.',
DeprecationWarning,
stacklevel=2)
self._discriminator = discriminator
@property
def optimizer(self) -> Optimizer:
"""
Get optimizer.
"""
return self._optimizer
@optimizer.setter
def optimizer(self, optimizer: Optional[Optimizer] = None) -> None:
"""
Set optimizer.
Args:
optimizer (Optimizer): optimizer to use with the generator.
Raises:
AquaError: invalid input.
"""
if optimizer:
if isinstance(optimizer, Optimizer):
self._optimizer = optimizer
else:
raise AquaError('Please provide an Optimizer object to use'
'as the generator optimizer.')
else:
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=self._snapshot_dir)
def construct_circuit(self, params=None):
"""
Construct generator circuit.
Args:
params (list | dict): parameters which should be used to run the generator.
Returns:
Instruction: construct the quantum circuit and return as gate
"""
if params is None:
return self.generator_circuit
if isinstance(params, (list, np.ndarray)):
params = dict(zip(self._free_parameters, params))
return self.generator_circuit.assign_parameters(params)
# self.generator_circuit.build(qc=qc, q=q)
# else:
# generator_circuit_copy = deepcopy(self.generator_circuit)
# generator_circuit_copy.params = params
# generator_circuit_copy.build(qc=qc, q=q)
# # return qc.copy(name='qc')
# return qc.to_instruction()
def get_output(self, quantum_instance, params=None, shots=None):
"""
Get classical data samples from the generator.
Running the quantum generator circuit results in a quantum state.
To train this generator with a classical discriminator, we need to sample classical outputs
by measuring the quantum state and mapping them to feature space defined by the training
data.
Args:
quantum_instance (QuantumInstance): Quantum Instance, used to run the generator
circuit.
params (numpy.ndarray): array or None, parameters which should
be used to run the generator, if None use self._params
shots (int): if not None use a number of shots that is different from the
number set in quantum_instance
Returns:
list: generated samples, array: sample occurrence in percentage
"""
instance_shots = quantum_instance.run_config.shots
q = QuantumRegister(sum(self._num_qubits), name='q')
qc = QuantumCircuit(q)
if params is None:
params = self._bound_parameters
qc.append(self.construct_circuit(params), q)
if quantum_instance.is_statevector:
pass
else:
c = ClassicalRegister(sum(self._num_qubits), name='c')
qc.add_register(c)
qc.measure(q, c)
if shots is not None:
quantum_instance.set_config(shots=shots)
result = quantum_instance.execute(qc)
generated_samples = []
if quantum_instance.is_statevector:
result = result.get_statevector(qc)
values = np.multiply(result, np.conj(result))
values = list(values.real)
keys = []
for j in range(len(values)):
keys.append(np.binary_repr(j, int(sum(self._num_qubits))))
else:
result = result.get_counts(qc)
keys = list(result)
values = list(result.values())
values = [float(v) / np.sum(values) for v in values]
generated_samples_weights = values
for i, _ in enumerate(keys):
index = 0
temp = []
for k, p in enumerate(self._num_qubits):
bin_rep = 0
j = 0
while j < p:
bin_rep += int(keys[i][index]) * 2**(int(p) - j - 1)
j += 1
index += 1
if len(self._num_qubits) > 1:
temp.append(self._data_grid[k][int(bin_rep)])
else:
temp.append(self._data_grid[int(bin_rep)])
generated_samples.append(temp)
# self.generator_circuit._probabilities = generated_samples_weights
if shots is not None:
# Restore the initial quantum_instance configuration
quantum_instance.set_config(shots=instance_shots)
return generated_samples, generated_samples_weights
def loss(self, x, weights): # pylint: disable=arguments-differ
"""
Loss function for training the generator's parameters.
Args:
x (numpy.ndarray): sample label (equivalent to discriminator output)
weights (numpy.ndarray): probability for measuring the sample
Returns:
float: loss function
"""
try:
# pylint: disable=no-member
loss = (-1) * np.dot(np.log(x).transpose(), weights)
except Exception: # pylint: disable=broad-except
loss = (-1) * np.dot(np.log(x), weights)
return loss.flatten()
def _get_objective_function(self, quantum_instance, discriminator):
"""
Get objective function
Args:
quantum_instance (QuantumInstance): used to run the quantum circuit.
discriminator (torch.nn.Module): discriminator network to compute the sample labels.
Returns:
objective_function: objective function for quantum generator optimization
"""
def objective_function(params):
"""
Objective function
Args:
params (numpy.ndarray): generator parameters
Returns:
self.loss: loss function
"""
generated_data, generated_prob = self.get_output(quantum_instance,
params=params,
shots=self._shots)
prediction_generated = discriminator.get_label(generated_data,
detach=True)
return self.loss(prediction_generated, generated_prob)
return objective_function
def _convert_to_gradient_function(self, gradient_object, quantum_instance,
discriminator):
"""
Convert to gradient function
Args:
gradient_object (Gradient): the gradient object to be used to
compute analytical gradients.
quantum_instance (QuantumInstance): used to run the quantum circuit.
discriminator (torch.nn.Module): discriminator network to compute the sample labels.
Returns:
gradient_function: gradient function that takes the current
parameter values and returns partial derivatives of the loss
function w.r.t. the variational parameters.
"""
def gradient_function(current_point):
"""
Gradient function
Args:
current_point (np.ndarray): Current values for the variational parameters.
Returns:
np.ndarray: array of partial derivatives of the loss
function w.r.t. the variational parameters.
"""
free_params = self._free_parameters
generated_data, _ = self.get_output(quantum_instance,
params=current_point,
shots=self._shots)
prediction_generated = discriminator.get_label(generated_data,
detach=True)
op = ~CircuitStateFn(primitive=self.generator_circuit)
grad_object = gradient_object.convert(operator=op,
params=free_params)
value_dict = {
free_params[i]: current_point[i]
for i in range(len(free_params))
}
analytical_gradients = np.array(
grad_object.assign_parameters(value_dict).eval())
loss_gradients = self.loss(prediction_generated,
analytical_gradients).real
return loss_gradients
return gradient_function
def train(self, quantum_instance=None, shots=None):
"""
Perform one training step w.r.t to the generator's parameters
Args:
quantum_instance (QuantumInstance): used to run the generator circuit.
shots (int): Number of shots for hardware or qasm execution.
Returns:
dict: generator loss(float) and updated parameters (array).
"""
self._shots = shots
# TODO Improve access to maxiter, say via options getter, to avoid private member access
# and since not all optimizers have that exact naming figure something better as well to
# allow the checking below to not have to warn if it has something else and max iterations
# is truly 1 anyway.
try:
if self._optimizer._maxiter != 1:
warnings.warn(
'Please set the the optimizer maxiter argument to 1 '
'to ensure that the generator '
'and discriminator are updated in an alternating fashion.')
except AttributeError:
maxiter = self._optimizer._options.get('maxiter')
if maxiter is not None and maxiter != 1:
warnings.warn(
'Please set the the optimizer maxiter argument to 1 '
'to ensure that the generator '
'and discriminator are updated in an alternating fashion.')
elif maxiter is None:
warnings.warn(
'Please ensure the optimizer max iterations are set to 1 '
'to ensure that the generator '
'and discriminator are updated in an alternating fashion.')
if isinstance(self._gradient_function, Gradient):
self._gradient_function = self._convert_to_gradient_function(
self._gradient_function, quantum_instance, self._discriminator)
objective = self._get_objective_function(quantum_instance,
self._discriminator)
self._bound_parameters, loss, _ = self._optimizer.optimize(
num_vars=len(self._bound_parameters),
objective_function=objective,
initial_point=self._bound_parameters,
gradient_function=self._gradient_function)
self._ret['loss'] = loss
self._ret['params'] = self._bound_parameters
return self._ret
def __init__(self,
bounds: np.ndarray,
num_qubits: List[int],
generator_circuit: Optional[
Union[UnivariateVariationalDistribution,
MultivariateVariationalDistribution,
QuantumCircuit]] = None,
init_params: Optional[Union[List[float], np.ndarray]] = None,
snapshot_dir: Optional[str] = None) -> None:
"""
Args:
bounds: k min/max data values [[min_1,max_1],...,[min_k,max_k]],
given input data dim k
num_qubits: k numbers of qubits to determine representation resolution,
i.e. n qubits enable the representation of 2**n values [n_1,..., n_k]
generator_circuit: a UnivariateVariationalDistribution for univariate data,
a MultivariateVariationalDistribution for multivariate data,
or a QuantumCircuit implementing the generator.
init_params: 1D numpy array or list, Initialization for
the generator's parameters.
snapshot_dir: str or None, if not None save the optimizer's parameter after every
update step to the given directory
Raises:
AquaError: Set multivariate variational distribution to represent multivariate data
"""
super().__init__()
self._bounds = bounds
self._num_qubits = num_qubits
self.generator_circuit = generator_circuit
if self.generator_circuit is None:
entangler_map = []
if np.sum(num_qubits) > 2:
for i in range(int(np.sum(num_qubits))):
entangler_map.append(
[i, int(np.mod(i + 1, np.sum(num_qubits)))])
else:
if np.sum(num_qubits) > 1:
entangler_map.append([0, 1])
if len(num_qubits) > 1:
num_qubits = list(map(int, num_qubits))
low = bounds[:, 0].tolist()
high = bounds[:, 1].tolist()
init_dist = MultivariateUniformDistribution(num_qubits,
low=low,
high=high)
q = QuantumRegister(sum(num_qubits))
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
# Set variational form
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = MultivariateVariationalDistribution(
num_qubits, var_form, init_params, low=low, high=high)
else:
init_dist = UniformDistribution(sum(num_qubits),
low=bounds[0],
high=bounds[1])
q = QuantumRegister(sum(num_qubits), name='q')
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = UnivariateVariationalDistribution(
int(np.sum(num_qubits)),
var_form,
init_params,
low=bounds[0],
high=bounds[1])
if len(num_qubits) > 1:
if isinstance(self.generator_circuit,
MultivariateVariationalDistribution):
pass
else:
raise AquaError('Set multivariate variational distribution '
'to represent multivariate data')
else:
if isinstance(self.generator_circuit,
UnivariateVariationalDistribution):
pass
else:
raise AquaError('Set univariate variational distribution '
'to represent univariate data')
# Set optimizer for updating the generator network
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=snapshot_dir)
if np.ndim(self._bounds) == 1:
bounds = np.reshape(self._bounds, (1, len(self._bounds)))
else:
bounds = self._bounds
for j, prec in enumerate(self._num_qubits):
# prepare data grid for dim j
grid = np.linspace(bounds[j, 0], bounds[j, 1], (2**prec))
if j == 0:
if len(self._num_qubits) > 1:
self._data_grid = [grid]
else:
self._data_grid = grid
self._grid_elements = grid
elif j == 1:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = [g_e]
temp0.append(g)
temp.append(temp0)
self._grid_elements = temp
else:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = deepcopy(g_e)
temp0.append(g)
temp.append(temp0)
self._grid_elements = deepcopy(temp)
self._data_grid = np.array(self._data_grid)
self._shots = None
self._discriminator = None
self._ret = {}
class QuantumGenerator(GenerativeNetwork):
"""
Quantum Generator.
The quantum generator is a parametrized quantum circuit which can be trained with the
:class:`~qiskit.aqua.algorithms.QGAN` algorithm
to generate a quantum state which approximates the probability
distribution of given training data. At the beginning of the training the parameters will
be set randomly, thus, the output will is random. Throughout the training the quantum
generator learns to represent the target distribution.
Eventually, the trained generator can be used for state preparation e.g. in QAE.
"""
def __init__(self,
bounds: np.ndarray,
num_qubits: List[int],
generator_circuit: Optional[
Union[UnivariateVariationalDistribution,
MultivariateVariationalDistribution,
QuantumCircuit]] = None,
init_params: Optional[Union[List[float], np.ndarray]] = None,
snapshot_dir: Optional[str] = None) -> None:
"""
Args:
bounds: k min/max data values [[min_1,max_1],...,[min_k,max_k]],
given input data dim k
num_qubits: k numbers of qubits to determine representation resolution,
i.e. n qubits enable the representation of 2**n values [n_1,..., n_k]
generator_circuit: a UnivariateVariationalDistribution for univariate data,
a MultivariateVariationalDistribution for multivariate data,
or a QuantumCircuit implementing the generator.
init_params: 1D numpy array or list, Initialization for
the generator's parameters.
snapshot_dir: str or None, if not None save the optimizer's parameter after every
update step to the given directory
Raises:
AquaError: Set multivariate variational distribution to represent multivariate data
"""
super().__init__()
self._bounds = bounds
self._num_qubits = num_qubits
self.generator_circuit = generator_circuit
if self.generator_circuit is None:
entangler_map = []
if np.sum(num_qubits) > 2:
for i in range(int(np.sum(num_qubits))):
entangler_map.append(
[i, int(np.mod(i + 1, np.sum(num_qubits)))])
else:
if np.sum(num_qubits) > 1:
entangler_map.append([0, 1])
if len(num_qubits) > 1:
num_qubits = list(map(int, num_qubits))
low = bounds[:, 0].tolist()
high = bounds[:, 1].tolist()
init_dist = MultivariateUniformDistribution(num_qubits,
low=low,
high=high)
q = QuantumRegister(sum(num_qubits))
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
# Set variational form
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = MultivariateVariationalDistribution(
num_qubits, var_form, init_params, low=low, high=high)
else:
init_dist = UniformDistribution(sum(num_qubits),
low=bounds[0],
high=bounds[1])
q = QuantumRegister(sum(num_qubits), name='q')
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = UnivariateVariationalDistribution(
int(np.sum(num_qubits)),
var_form,
init_params,
low=bounds[0],
high=bounds[1])
if len(num_qubits) > 1:
if isinstance(self.generator_circuit,
MultivariateVariationalDistribution):
pass
else:
raise AquaError('Set multivariate variational distribution '
'to represent multivariate data')
else:
if isinstance(self.generator_circuit,
UnivariateVariationalDistribution):
pass
else:
raise AquaError('Set univariate variational distribution '
'to represent univariate data')
# Set optimizer for updating the generator network
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=snapshot_dir)
if np.ndim(self._bounds) == 1:
bounds = np.reshape(self._bounds, (1, len(self._bounds)))
else:
bounds = self._bounds
for j, prec in enumerate(self._num_qubits):
# prepare data grid for dim j
grid = np.linspace(bounds[j, 0], bounds[j, 1], (2**prec))
if j == 0:
if len(self._num_qubits) > 1:
self._data_grid = [grid]
else:
self._data_grid = grid
self._grid_elements = grid
elif j == 1:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = [g_e]
temp0.append(g)
temp.append(temp0)
self._grid_elements = temp
else:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = deepcopy(g_e)
temp0.append(g)
temp.append(temp0)
self._grid_elements = deepcopy(temp)
self._data_grid = np.array(self._data_grid)
self._shots = None
self._discriminator = None
self._ret = {}
def set_seed(self, seed):
"""
Set seed.
Args:
seed (int): seed
"""
aqua_globals.random_seed = seed
def set_discriminator(self, discriminator):
"""
Set discriminator network.
Args:
discriminator (Discriminator): Discriminator used to compute the loss function.
"""
self._discriminator = discriminator
def construct_circuit(self, params=None):
"""
Construct generator circuit.
Args:
params (numpy.ndarray): parameters which should be used to run the generator,
if None use self._params
Returns:
Instruction: construct the quantum circuit and return as gate
"""
q = QuantumRegister(sum(self._num_qubits), name='q')
qc = QuantumCircuit(q)
if params is None:
self.generator_circuit.build(qc=qc, q=q)
else:
generator_circuit_copy = deepcopy(self.generator_circuit)
generator_circuit_copy.params = params
generator_circuit_copy.build(qc=qc, q=q)
# return qc.copy(name='qc')
return qc.to_instruction()
def get_output(self,
quantum_instance,
qc_state_in=None,
params=None,
shots=None):
"""
Get classical data samples from the generator.
Running the quantum generator circuit results in a quantum state.
To train this generator with a classical discriminator, we need to sample classical outputs
by measuring the quantum state and mapping them to feature space defined by the training
data.
Args:
quantum_instance (QuantumInstance): Quantum Instance, used to run the generator
circuit.
qc_state_in (QuantumCircuit): deprecated
params (numpy.ndarray): array or None, parameters which should
be used to run the generator, if None use self._params
shots (int): if not None use a number of shots that is different from the
number set in quantum_instance
Returns:
list: generated samples, array: sample occurrence in percentage
"""
instance_shots = quantum_instance.run_config.shots
q = QuantumRegister(sum(self._num_qubits), name='q')
qc = QuantumCircuit(q)
qc.append(self.construct_circuit(params), q)
if quantum_instance.is_statevector:
pass
else:
c = ClassicalRegister(sum(self._num_qubits), name='c')
qc.add_register(c)
qc.measure(q, c)
if shots is not None:
quantum_instance.set_config(shots=shots)
result = quantum_instance.execute(qc)
generated_samples = []
if quantum_instance.is_statevector:
result = result.get_statevector(qc)
values = np.multiply(result, np.conj(result))
values = list(values.real)
keys = []
for j in range(len(values)):
keys.append(np.binary_repr(j, int(sum(self._num_qubits))))
else:
result = result.get_counts(qc)
keys = list(result)
values = list(result.values())
values = [float(v) / np.sum(values) for v in values]
generated_samples_weights = values
for i, _ in enumerate(keys):
index = 0
temp = []
for k, p in enumerate(self._num_qubits):
bin_rep = 0
j = 0
while j < p:
bin_rep += int(keys[i][index]) * 2**(int(p) - j - 1)
j += 1
index += 1
if len(self._num_qubits) > 1:
temp.append(self._data_grid[k][int(bin_rep)])
else:
temp.append(self._data_grid[int(bin_rep)])
generated_samples.append(temp)
self.generator_circuit._probabilities = generated_samples_weights
if shots is not None:
# Restore the initial quantum_instance configuration
quantum_instance.set_config(shots=instance_shots)
return generated_samples, generated_samples_weights
def loss(self, x, weights): # pylint: disable=arguments-differ
"""
Loss function for training the generator's parameters.
Args:
x (numpy.ndarray): sample label (equivalent to discriminator output)
weights (numpy.ndarray): probability for measuring the sample
Returns:
float: loss function
"""
try:
# pylint: disable=no-member
loss = (-1) * np.dot(np.log(x).transpose(), weights)
except Exception: # pylint: disable=broad-except
loss = (-1) * np.dot(np.log(x), weights)
return loss.flatten()
def _get_objective_function(self, quantum_instance, discriminator):
"""
Get objective function
Args:
quantum_instance (QuantumInstance): used to run the quantum circuit.
discriminator (torch.nn.Module): discriminator network to compute the sample labels.
Returns:
objective_function: objective function for quantum generator optimization
"""
def objective_function(params):
"""
Objective function
Args:
params (numpy.ndarray): generator parameters
Returns:
self.loss: loss function
"""
generated_data, generated_prob = self.get_output(quantum_instance,
params=params,
shots=self._shots)
prediction_generated = discriminator.get_label(generated_data,
detach=True)
return self.loss(prediction_generated, generated_prob)
return objective_function
def train(self, quantum_instance=None, shots=None):
"""
Perform one training step w.r.t to the generator's parameters
Args:
quantum_instance (QuantumInstance): used to run the generator circuit.
shots (int): Number of shots for hardware or qasm execution.
Returns:
dict: generator loss(float) and updated parameters (array).
"""
self._shots = shots
# Force single optimization iteration
self._optimizer._maxiter = 1
self._optimizer._t = 0
objective = self._get_objective_function(quantum_instance,
self._discriminator)
self.generator_circuit.params, loss, _ = \
self._optimizer.optimize(num_vars=len(self.generator_circuit.params),
objective_function=objective,
initial_point=self.generator_circuit.params)
self._ret['loss'] = loss
self._ret['params'] = self.generator_circuit.params
return self._ret
def test_adam(self):
""" adam test """
optimizer = ADAM(maxiter=10000, tol=1e-06)
res = self._optimize(optimizer)
self.assertLessEqual(res[2], 10000)
class QuantumGenerator(GenerativeNetwork):
"""
Generator
"""
CONFIGURATION = {
'name': 'QuantumGenerator',
'description': 'qGAN Generator Network',
'input_schema': {
'$schema': 'http://json-schema.org/draft-07/schema#',
'id': 'generator_schema',
'type': 'object',
'properties': {
'bounds': {
'type': 'array'
},
'num_qubits': {
'type': 'array'
},
'init_params': {
'type': ['array', 'null'],
'default': None
},
'snapshot_dir': {
'type': ['string', 'null'],
'default': None
}
},
'additionalProperties': False
}
}
def __init__(self,
bounds,
num_qubits,
generator_circuit=None,
init_params=None,
snapshot_dir=None):
"""
Initialize the generator network.
Args:
bounds (numpy.ndarray): k min/max data values [[min_1,max_1],...,[min_k,max_k]],
given input data dim k
num_qubits (list): k numbers of qubits to determine representation resolution,
i.e. n qubits enable the representation of 2**n values [n_1,..., n_k]
generator_circuit (Union): generator circuit
UnivariateVariationalDistribution for univariate data/
MultivariateVariationalDistribution for multivariate data, Quantum circuit
to implement the generator.
init_params (Union(list, numpy.ndarray)): 1D numpy array or list, Initialization for
the generator's parameters.
snapshot_dir (str): str or None, if not None save the optimizer's parameter after every
update step to the given directory
Raises:
AquaError: Set multivariate variational distribution to represent multivariate data
"""
super().__init__()
self._bounds = bounds
self._num_qubits = num_qubits
self.generator_circuit = generator_circuit
if self.generator_circuit is None:
entangler_map = []
if np.sum(num_qubits) > 2:
for i in range(int(np.sum(num_qubits))):
entangler_map.append(
[i, int(np.mod(i + 1, np.sum(num_qubits)))])
else:
if np.sum(num_qubits) > 1:
entangler_map.append([0, 1])
if len(num_qubits) > 1:
num_qubits = list(map(int, num_qubits))
low = bounds[:, 0].tolist()
high = bounds[:, 1].tolist()
init_dist = MultivariateUniformDistribution(num_qubits,
low=low,
high=high)
q = QuantumRegister(sum(num_qubits))
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
# Set variational form
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = MultivariateVariationalDistribution(
num_qubits, var_form, init_params, low=low, high=high)
else:
init_dist = UniformDistribution(sum(num_qubits),
low=bounds[0],
high=bounds[1])
q = QuantumRegister(sum(num_qubits), name='q')
qc = QuantumCircuit(q)
init_dist.build(qc, q)
init_distribution = Custom(num_qubits=sum(num_qubits),
circuit=qc)
var_form = RY(sum(num_qubits),
depth=1,
initial_state=init_distribution,
entangler_map=entangler_map,
entanglement_gate='cz')
if init_params is None:
init_params = aqua_globals.random.rand(
var_form.num_parameters) * 2 * 1e-2
# Set generator circuit
self.generator_circuit = UnivariateVariationalDistribution(
int(np.sum(num_qubits)),
var_form,
init_params,
low=bounds[0],
high=bounds[1])
if len(num_qubits) > 1:
if isinstance(self.generator_circuit,
MultivariateVariationalDistribution):
pass
else:
raise AquaError('Set multivariate variational distribution '
'to represent multivariate data')
else:
if isinstance(self.generator_circuit,
UnivariateVariationalDistribution):
pass
else:
raise AquaError('Set univariate variational distribution '
'to represent univariate data')
# Set optimizer for updating the generator network
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=snapshot_dir)
if np.ndim(self._bounds) == 1:
bounds = np.reshape(self._bounds, (1, len(self._bounds)))
else:
bounds = self._bounds
for j, prec in enumerate(self._num_qubits):
# prepare data grid for dim j
grid = np.linspace(bounds[j, 0], bounds[j, 1], (2**prec))
if j == 0:
if len(self._num_qubits) > 1:
self._data_grid = [grid]
else:
self._data_grid = grid
self._grid_elements = grid
elif j == 1:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = [g_e]
temp0.append(g)
temp.append(temp0)
self._grid_elements = temp
else:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = deepcopy(g_e)
temp0.append(g)
temp.append(temp0)
self._grid_elements = deepcopy(temp)
self._data_grid = np.array(self._data_grid)
self._shots = None
self._discriminator = None
self._ret = {}
@classmethod
def init_params(cls, params):
"""
Initialize via parameters dictionary and algorithm input instance.
Args:
params (dict): parameters dictionary
Returns:
QuantumGenerator: vqe object
Raises:
AquaError: invalid input
"""
generator_params = params.get(Pluggable.SECTION_KEY_GENERATIVE_NETWORK)
bounds = generator_params.get('bounds')
if bounds is None:
raise AquaError("Data value bounds are required.")
num_qubits = generator_params.get('num_qubits')
if num_qubits is None:
raise AquaError("Numbers of qubits per dimension required.")
init_params = generator_params.get('init_params')
snapshot_dir = generator_params.get('snapshot_dir')
return cls(bounds,
num_qubits,
generator_circuit=None,
init_params=init_params,
snapshot_dir=snapshot_dir)
@classmethod
def get_section_key_name(cls):
return Pluggable.SECTION_KEY_GENERATIVE_NETWORK
def set_seed(self, seed):
"""
Set seed.
Args:
seed (int): seed
"""
aqua_globals.random_seed = seed
def set_discriminator(self, discriminator):
"""
Set discriminator
Args:
discriminator (Discriminator): Discriminator used to compute the loss function.
"""
self._discriminator = discriminator
def construct_circuit(self, params=None):
"""
Construct generator circuit.
Args:
params (numpy.ndarray): parameters which should be used to run the generator,
if None use self._params
Returns:
Instruction: construct the quantum circuit and return as gate
"""
q = QuantumRegister(sum(self._num_qubits), name='q')
qc = QuantumCircuit(q)
if params is None:
self.generator_circuit.build(qc=qc, q=q)
else:
generator_circuit_copy = deepcopy(self.generator_circuit)
generator_circuit_copy.params = params
generator_circuit_copy.build(qc=qc, q=q)
# return qc.copy(name='qc')
return qc.to_instruction()
def get_output(self,
quantum_instance,
qc_state_in=None,
params=None,
shots=None):
"""
Get data samples from the generator.
Args:
quantum_instance (QuantumInstance): Quantum Instance, used to run the generator
circuit.
qc_state_in (QuantumCircuit): depreciated
params (numpy.ndarray): array or None, parameters which should
be used to run the generator,
if None use self._params
shots (int): if not None use a number of shots that is different from the
number set in quantum_instance
Returns:
list: generated samples, array: sample occurrence in percentage
"""
instance_shots = quantum_instance.run_config.shots
q = QuantumRegister(sum(self._num_qubits), name='q')
qc = QuantumCircuit(q)
qc.append(self.construct_circuit(params), q)
if quantum_instance.is_statevector:
pass
else:
c = ClassicalRegister(sum(self._num_qubits), name='c')
qc.add_register(c)
qc.measure(q, c)
if shots is not None:
quantum_instance.set_config(shots=shots)
result = quantum_instance.execute(qc)
generated_samples = []
if quantum_instance.is_statevector:
result = result.get_statevector(qc)
values = np.multiply(result, np.conj(result))
values = list(values.real)
keys = []
for j in range(len(values)):
keys.append(np.binary_repr(j, int(sum(self._num_qubits))))
else:
result = result.get_counts(qc)
keys = list(result)
values = list(result.values())
values = [float(v) / np.sum(values) for v in values]
generated_samples_weights = values
for i, _ in enumerate(keys):
index = 0
temp = []
for k, p in enumerate(self._num_qubits):
bin_rep = 0
j = 0
while j < p:
bin_rep += int(keys[i][index]) * 2**(int(p) - j - 1)
j += 1
index += 1
if len(self._num_qubits) > 1:
temp.append(self._data_grid[k][int(bin_rep)])
else:
temp.append(self._data_grid[int(bin_rep)])
generated_samples.append(temp)
self.generator_circuit._probabilities = generated_samples_weights
if shots is not None:
# Restore the initial quantum_instance configuration
quantum_instance.set_config(shots=instance_shots)
return generated_samples, generated_samples_weights
def loss(self, x, weights): # pylint: disable=arguments-differ
"""
Loss function
Args:
x (numpy.ndarray): sample label (equivalent to discriminator output)
weights (numpy.ndarray): probability for measuring the sample
Returns:
float: loss function
"""
try:
# pylint: disable=no-member
loss = (-1) * np.dot(np.log(x).transpose(), weights)
except Exception: # pylint: disable=broad-except
loss = (-1) * np.dot(np.log(x), weights)
return loss.flatten()
def _get_objective_function(self, quantum_instance, discriminator):
"""
Get objective function
Args:
quantum_instance (QuantumInstance): used to run the quantum circuit.
discriminator (torch.nn.Module): discriminator network to compute the sample labels.
Returns:
objective_function: objective function for quantum generator optimization
"""
def objective_function(params):
"""
Objective function
Args:
params (numpy.ndarray): generator parameters
Returns:
self.loss: loss function
"""
generated_data, generated_prob = self.get_output(quantum_instance,
params=params,
shots=self._shots)
prediction_generated = discriminator.get_label(generated_data,
detach=True)
return self.loss(prediction_generated, generated_prob)
return objective_function
def train(self, quantum_instance=None, shots=None):
"""
Perform one training step w.r.t to the generator's parameters
Args:
quantum_instance (QuantumInstance): used to run the generator circuit.
shots (int): Number of shots for hardware or qasm execution.
Returns:
dict: generator loss(float) and updated parameters (array).
"""
self._shots = shots
# Force single optimization iteration
self._optimizer._maxiter = 1
self._optimizer._t = 0
objective = self._get_objective_function(quantum_instance,
self._discriminator)
self.generator_circuit.params, loss, _ = \
self._optimizer.optimize(num_vars=len(self.generator_circuit.params),
objective_function=objective,
initial_point=self.generator_circuit.params)
self._ret['loss'] = loss
self._ret['params'] = self.generator_circuit.params
return self._ret
chosen_neg_label_idx = neg_label[np.random.permutation(len(neg_label))[:neg_sample]]
print("Postive sample num: %d" % len(pos_label))
print("Negative sample num: %d" % len(neg_label))
# Construct dict to feed QSVM
training_input = {
0: df_train_q[chosen_pos_label_idx],
1: df_train_q[chosen_neg_label_idx]
}
test_input = df_test_q
###### data prepared
print("data prepared.")
###### building quantum dude
seed = 10598
# seed = 1024
var_form = variational_forms.RYRZ(2)
feature_map = ZZFeatureMap(feature_dimension=len(mvp_col), reps=2, entanglement='linear')
qsvm = VQC(ADAM(100), feature_map, var_form, training_input)
backend = BasicAer.get_backend('qasm_simulator')
quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=seed, seed_transpiler=seed, optimization_level=3)
result = qsvm.run(quantum_instance)
y_pred = qsvm.predict(df_train_q)[1]
print("Final train acc: %f\nFinal train F1:%f" % (np.mean(y_pred == y_train), f1_score(y_pred, y_train)))
y_pred = qsvm.predict(df_test_q)[1]
# print(y_pred)
record_test_result_for_kaggle(y_pred, submission_file="quantum_submission.csv")
def __init__(self,
bounds: np.ndarray,
num_qubits: List[int],
generator_circuit: Optional[
Union[UnivariateVariationalDistribution,
MultivariateVariationalDistribution,
QuantumCircuit]] = None,
init_params: Optional[Union[List[float], np.ndarray]] = None,
optimizer: Optional[Optimizer] = None,
snapshot_dir: Optional[str] = None) -> None:
"""
Args:
bounds: k min/max data values [[min_1,max_1],...,[min_k,max_k]],
given input data dim k
num_qubits: k numbers of qubits to determine representation resolution,
i.e. n qubits enable the representation of 2**n values [n_1,..., n_k]
generator_circuit: a UnivariateVariationalDistribution for univariate data,
a MultivariateVariationalDistribution for multivariate data,
or a QuantumCircuit implementing the generator.
init_params: 1D numpy array or list, Initialization for
the generator's parameters.
optimizer: optimizer to be used for the training of the generator
snapshot_dir: str or None, if not None save the optimizer's parameter after every
update step to the given directory
Raises:
AquaError: Set multivariate variational distribution to represent multivariate data
"""
super().__init__()
self._bounds = bounds
self._num_qubits = num_qubits
self.generator_circuit = generator_circuit
if generator_circuit is None:
circuit = QuantumCircuit(sum(num_qubits))
circuit.h(circuit.qubits)
var_form = TwoLocal(sum(num_qubits),
'ry',
'cz',
reps=1,
entanglement='circular')
circuit.compose(var_form, inplace=True)
# Set generator circuit
self.generator_circuit = circuit
if isinstance(generator_circuit,
(UnivariateVariationalDistribution,
MultivariateVariationalDistribution)):
warnings.warn(
'Passing a UnivariateVariationalDistribution or MultivariateVariational'
'Distribution is as ``generator_circuit`` is deprecated as of Aqua 0.8.0 '
'and the support will be removed no earlier than 3 months after the '
'release data. You should pass as QuantumCircuit instead.',
DeprecationWarning,
stacklevel=2)
self._free_parameters = generator_circuit._var_form_params
self.generator_circuit = generator_circuit._var_form
else:
self._free_parameters = sorted(self.generator_circuit.parameters,
key=lambda p: p.name)
if init_params is None:
init_params = aqua_globals.random.random(
self.generator_circuit.num_parameters) * 2e-2
self._bound_parameters = init_params
# Set optimizer for updating the generator network
if optimizer:
self._optimizer = optimizer
else:
self._optimizer = ADAM(maxiter=1,
tol=1e-6,
lr=1e-3,
beta_1=0.7,
beta_2=0.99,
noise_factor=1e-6,
eps=1e-6,
amsgrad=True,
snapshot_dir=snapshot_dir)
if np.ndim(self._bounds) == 1:
bounds = np.reshape(self._bounds, (1, len(self._bounds)))
else:
bounds = self._bounds
for j, prec in enumerate(self._num_qubits):
# prepare data grid for dim j
grid = np.linspace(bounds[j, 0], bounds[j, 1], (2**prec))
if j == 0:
if len(self._num_qubits) > 1:
self._data_grid = [grid]
else:
self._data_grid = grid # type: ignore
self._grid_elements = grid
elif j == 1:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = [g_e]
temp0.append(g)
temp.append(temp0)
self._grid_elements = temp # type: ignore
else:
self._data_grid.append(grid)
temp = []
for g_e in self._grid_elements:
for g in grid:
temp0 = deepcopy(g_e)
temp0.append(g)
temp.append(temp0)
self._grid_elements = deepcopy(temp) # type: ignore
self._data_grid = np.array(self._data_grid) # type: ignore
self._shots = None
self._discriminator = None
self._ret = {} # type: Dict[str, Any]
