ce7dc229bea184b9d606a1fe6a19a30c2c4a0d36,aae/adversarial_autoencoder.py,AdversarialAutoencoder,train,#AdversarialAutoencoder#,116
Before Change
// Train the discriminator
d_loss_real = self.discriminator.train_on_batch(latent_real, valid)
d_loss_fake = self.discriminator.train_on_batch(latent_fake, fake)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
After Change
// Train the discriminator
d_loss_real = self.discriminator.train_on_batch(latent_real, np.ones((half_batch, 1)))
d_loss_fake = self.discriminator.train_on_batch(latent_fake, np.zeros((half_batch, 1)))
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 2
Instances
Project Name: eriklindernoren/Keras-GAN
Commit Name: ce7dc229bea184b9d606a1fe6a19a30c2c4a0d36
Time: 2018-05-11
Author: eriklindernoren@gmail.com
File Name: aae/adversarial_autoencoder.py
Class Name: AdversarialAutoencoder
Method Name: train
Project Name: eriklindernoren/Keras-GAN
Commit Name: cf65784f7297dca491436112b9a5689ecd7533ec
Time: 2018-05-15
Author: eriklindernoren@live.se
File Name: wgan/wgan.py
Class Name: WGAN
Method Name: train