3cba7783cb805459d26918be7a56b0e8b8fd3bc9,context_encoder.py,ContextEncoder,train,#ContextEncoder#Any#Any#Any#,140

Before Change

            generated_missing_parts = self.generator.predict(masked_imgs)

            // Concatenate the true and generated samples
            imgs_x = np.vstack((missing_parts, generated_missing_parts))

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

After Change

            gen_missing = self.generator.predict(masked_imgs)

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

            // Train the discriminator
            d_loss_real = self.discriminator.train_on_batch(missing, valid)
            d_loss_fake = self.discriminator.train_on_batch(gen_missing, fake)
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

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

Instances