Why is tanh not used as activation at the last layer of generator?

[sidak]

The DCGAN paper mentions about the use of tanh. Is there any reason why it is not used? What is the difference in the results in both cases.

Thank you.

[sidak]

@mattya More specifically in the below line of code.

x = (self.dc4(h))

[praveenkumarchandaliya]

the last layer in the generator is tanh because it making value between -1 and 1. and make over the network is more stable in the case of color image and video.