Hello, author, I have some questions about gated convolution, hope to answer！
 In the paper, there is no bias in its formula (i.e. sigmoid (Gatingy,x)), so the probability value of the missing area after sigmoid is 0, which can shield the invalid value of the missing area. 
 But I read your code, and the bias default is True, so the probability of the missing area is not 0. Isn't it impossible to shield?
 Finally, wish you all the best, good job and good body!!