NumPyDiscriminator

class NumPyDiscriminator(n_features=1, n_out=1)[source]

Discriminator based on NumPy

Parameters

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

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

Attributes

NumPyDiscriminator.discriminator_net

Get discriminator

Methods

NumPyDiscriminator.get_label(x[, detach])

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

NumPyDiscriminator.load_model(load_dir)

Load discriminator model

NumPyDiscriminator.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

NumPyDiscriminator.save_model(snapshot_dir)

Save discriminator model

NumPyDiscriminator.set_seed(seed)

Set seed.

NumPyDiscriminator.train(data, weights[, …])

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