qiskit.aqua.components.neural_networks.NumPyDiscriminator
class NumPyDiscriminator(n_features=1, n_out=1)
Discriminator based on NumPy
Parameters
- n_features (
int) – Dimension of input data vector. - n_out (
int) – Dimension of the discriminator’s output vector.
__init__
__init__(n_features=1, n_out=1)
Parameters
- n_features (
int) – Dimension of input data vector. - n_out (
int) – Dimension of the discriminator’s output vector.
Methods
__init__([n_features, n_out]) | type n_featuresint |
get_label(x[, detach]) | Get data sample labels, i.e. true or fake. |
load_model(load_dir) | Load discriminator model |
loss(x, y[, weights]) | Loss function :param x: sample label (equivalent to discriminator output) :type x: numpy.ndarray :param y: target label :type y: numpy.ndarray :param weights: customized scaling for each sample (optional) :type weights: numpy.ndarray |
save_model(snapshot_dir) | Save discriminator model |
set_seed(seed) | Set seed. |
train(data, weights[, penalty, …]) | Perform one training step w.r.t to the discriminator’s parameters |
Attributes
discriminator_net | Get discriminator |
discriminator_net
Get discriminator
Returns
discriminator object
Return type
DiscriminatorNet
get_label
get_label(x, detach=False)
Get data sample labels, i.e. true or fake.
Parameters
- x (numpy.ndarray) – Discriminator input, i.e. data sample.
- detach (bool) – depreciated for numpy network
Returns
Discriminator output, i.e. data label
Return type
numpy.ndarray
load_model
load_model(load_dir)
Load discriminator model
Parameters
load_dir (str) – file with stored pytorch discriminator model to be loaded
loss
loss(x, y, weights=None)
Loss function :param x: sample label (equivalent to discriminator output) :type x: numpy.ndarray :param y: target label :type y: numpy.ndarray :param weights: customized scaling for each sample (optional) :type weights: numpy.ndarray
Returns
loss function
Return type
float
save_model
save_model(snapshot_dir)
Save discriminator model
Parameters
snapshot_dir (str) – directory path for saving the model
set_seed
set_seed(seed)
Set seed. :param seed: seed :type seed: int
train
train(data, weights, penalty=False, quantum_instance=None, shots=None)
Perform one training step w.r.t to the discriminator’s parameters
Parameters
- 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
with Discriminator loss and updated parameters.
Return type
dict