Hands-On Transfer Learning with Python

Total variation loss

It was observed that optimization to reduce only the style and content losses led to highly pixelated and noisy outputs. To cover the same, total variation loss was introduced. The total variation loss is analogous to regularization loss. This is introduced for ensuring spatial continuity and smoothness in the generated image to avoid noisy and overly pixelated results. The same is defined in the function as follows:

def total_variation_loss(x):    a = K.square(        x[:, :img_height - 1, :img_width - 1, :] - x[:, 1:, :img_width           - 1, :])    b = K.square(        x[:, :img_height - 1, :img_width - 1, :] - x[:, :img_height -           1, 1:, :])    return K.sum(K.pow(a + b, 1.25))