Generator loss in Super-resolution GAN.

[tahmid32]

Hi there! Thanks for the good work. I am using Super-resolution GAN code from here for my academic project. Here in the code snippet:

        """
        Train the generator network
        """

        # Sample a batch of images
        high_resolution_images, low_resolution_images = sample_images(data_dir=data_dir, batch_size=batch_size,
                                                                      low_resolution_shape=low_resolution_shape,
                                                                      high_resolution_shape=high_resolution_shape)
        # Normalize images
        high_resolution_images = high_resolution_images / 127.5 - 1.
        low_resolution_images = low_resolution_images / 127.5 - 1.

        # Extract feature maps for real high-resolution images
        image_features = vgg.predict(high_resolution_images)

        # Train the generator network
        g_loss = adversarial_model.train_on_batch([low_resolution_images, high_resolution_images],
                                         [real_labels, image_features])

        print("g_loss:", g_loss)

When g_loss is printed, 3 losses are shown. My query is that middle one among the three losses belongs to which category. Thanks and regards.