Closed chojuahn closed 4 years ago
I don't understand why there is synthetic_image_batch fed to train refiner_model for x and y. Shouldn't this be x as refiner_model and y as real_image_batch respectively?
synthetic_image_batch
refiner_model
real_image_batch
self_regularization_loss is designed for ||R(x) - x|| where x is synthetic_image, which makes sense having synthetic_image_batch for both x and y.
self_regularization_loss
synthetic_image
I don't understand why there is
synthetic_image_batch
fed to trainrefiner_model
for x and y. Shouldn't this be x asrefiner_model
and y asreal_image_batch
respectively?