Article | 11-January-2021
encoding→decoding, the generator of this paper chooses the network model of the U-net structure. The discriminator uses the structure of an area discriminator.
1)
Network structure of generator model based on U-NET network
In order to obtain valuable information from the conditional background picture, the network structure of the generator in this paper adopts the U-net network structure of cascaded encoding and decoding. The U-net network was first proposed by Olaf et al. to be applied to the full
Haoyang Liu,
Zhiyi Hu,
Jun Yu,
Shouyi Gao
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 4, 66–74