qiskit.aqua.components.neural_networks.GenerativeNetwork

class GenerativeNetwork

Base class for generative Quantum and Classical Neural Networks.

This method should initialize the module, but raise an exception if a required component of the module is not available.

abstract __init__()

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__()	Initialize self.
get_output(quantum_instance, params, shots)	Apply quantum/classical neural network to given input and get the respective output
loss()	Loss function used for optimization
set_seed(seed)	Set seed.
train([quantum_instance, shots])	Perform one training step w.r.t to the generator’s parameters

abstract get_output(quantum_instance, params, shots)

Apply quantum/classical neural network to given input and get the respective output

Parâmetros

• quantum_instance (QuantumInstance) – Quantum Instance, used to run the generator circuit.

• params (numpy.ndarray) – 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

Retorna

Neural network output

Levanta

NotImplementedError – not implemented

abstract loss()

Loss function used for optimization

abstract set_seed(seed)

Set seed.

Parâmetros

seed (int) – seed

Levanta

NotImplementedError – not implemented

abstract train(quantum_instance=None, shots=None)

Perform one training step w.r.t to the generator’s parameters

Parâmetros

• quantum_instance (QuantumInstance) – used to run generator network. Ignored for a classical network.

• shots (int) – Number of shots for hardware or qasm execution. Ignored for classical network

Retorna

generator loss and updated parameters.

Tipo de retorno

dict

Levanta

NotImplementedError – not implemented