It really surprised me a lot

[Breezewrf]

after my "training" on restoration task, I am curious about the loss function -- mse, the parameters including both restoration generated image and ground truth, some minutes after, a function training was finished,
and when I add a watermark different from further one, result as following:

last, as far as I am concerned, this algorithm is unrealistic, on the other hand, maybe I have mistaken something because I just met this project yesterday

[arnavmehta7]

thats because you need to bitwise_not(mask)