744353138995f1b15933be6ee2d39f7b83ee1b1f,adversarial_autoencoder.py,AdversarialAutoencoder,train,#AdversarialAutoencoder#Any#Any#Any#,108

Before Change

            encoded_x = np.concatenate((latent_real, latent_fake))

            // First half are valid and second are fake
            valid_y = np.array([1] * half_batch + [0] * half_batch).reshape(-1, 1)

            // Train the discriminator
            d_loss = self.discriminator.train_on_batch([encoded_x, imgs_x], [imgs_x, valid_y])

After Change

            latent_real = np.random.normal(size=(half_batch, self.encoded_dim))

            valid = np.ones((half_batch, 1))
            fake = np.zeros((half_batch, 1))

            // Train the discriminator
            d_loss_real = self.discriminator.train_on_batch([latent_real, imgs], [imgs, valid])
            d_loss_fake = self.discriminator.train_on_batch([latent_fake, gen_imgs], [gen_imgs, fake])
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)


            // ---------------------

Instances