qiskit.aqua.components.neural_networks.PyTorchDiscriminator

class PyTorchDiscriminator(n_features=1, n_out=1)

Discriminator based on PyTorch

매개변수

• n_features (int) – Dimension of input data vector.

• n_out (int) – Dimension of the discriminator’s output vector.

예외

MissingOptionalLibraryError – Pytorch not installed

__init__(n_features=1, n_out=1)

매개변수

• n_features (int) – Dimension of input data vector.

• n_out (int) – Dimension of the discriminator’s output vector.

예외

MissingOptionalLibraryError – Pytorch not installed

Methods

__init__([n_features, n_out])	type n_features int
get_label(x[, detach])	Get data sample labels, i.e. true or fake.
gradient_penalty(x[, lambda_, k, c])	Compute gradient penalty for discriminator optimization
load_model(load_dir)	Load discriminator model
loss(x, y[, weights])	Loss function
save_model(snapshot_dir)	Save discriminator model
set_seed(seed)	Set seed.
train(data, weights[, penalty, …])	Perform one training step w.r.t.

Attributes

discriminator_net

Get discriminator

property discriminator_net

Get discriminator

반환값

discriminator object

반환 형식

object

get_label(x, detach=False)

Get data sample labels, i.e. true or fake.

매개변수

• x (Union(numpy.ndarray, torch.Tensor)) – Discriminator input, i.e. data sample.

• detach (bool) – if None detach from torch tensor variable (optional)

반환값

Discriminator output, i.e. data label

반환 형식

torch.Tensor

gradient_penalty(x, lambda_=5.0, k=0.01, c=1.0)

Compute gradient penalty for discriminator optimization

매개변수

• x (numpy.ndarray) – Generated data sample.

• lambda (float) – Gradient penalty coefficient 1.

• k (float) – Gradient penalty coefficient 2.

• c (float) – Gradient penalty coefficient 3.

반환값

Gradient penalty.

반환 형식

torch.Tensor

load_model(load_dir)

Load discriminator model

매개변수

load_dir (str) – file with stored pytorch discriminator model to be loaded

loss(x, y, weights=None)

Loss function

매개변수

• x (torch.Tensor) – Discriminator output.

• y (torch.Tensor) – Label of the data point

• weights (torch.Tensor) – Data weights.

반환값

Loss w.r.t to the generated data points.

반환 형식

torch.Tensor

save_model(snapshot_dir)

Save discriminator model

매개변수

snapshot_dir (str) – directory path for saving the model

set_seed(seed)

Set seed.

매개변수

seed (int) – seed

train(data, weights, penalty=True, quantum_instance=None, shots=None)

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

매개변수

• data (tuple) – real_batch: torch.Tensor, Training data batch. generated_batch: numpy array, Generated data batch.

• weights (tuple) – real problem, generated problem

• penalty (bool) – Indicate whether or not penalty function is applied to the loss function.

• quantum_instance (QuantumInstance) – Quantum Instance (depreciated)

• shots (int) – Number of shots for hardware or qasm execution. Not used for classical network (only quantum ones)

반환값

with Discriminator loss (torch.Tensor) and updated parameters (array).

반환 형식

dict