3cba7783cb805459d26918be7a56b0e8b8fd3bc9,gan.py,GAN,train,#GAN#Any#Any#Any#,93

Before Change

            gen_imgs = self.generator.predict(noise)

            // Concatenate the true and generated samples
            imgs_x = np.concatenate((imgs, gen_imgs), axis=0)

            // The discriminator wants to label the true samples as valid (ones) and
            // the generated images as fake (zeros)
            valid_y = np.array([1] * half_batch + [0] * half_batch).reshape(-1, 1)

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

After Change

            gen_imgs = self.generator.predict(noise)

            // Train the discriminator
            d_loss_real = self.discriminator.train_on_batch(imgs, np.ones((half_batch, 1)))
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, np.zeros((half_batch, 1)))
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)


            // ---------------------
            //  Train Generator

Instances