the SAN branch consume a large amount of memory

[kitlien]

Hi,
When I training san on imagenet, which has 1000 class numbers of source target . And the base network before san has 256 outputs. The 'ad_net' branch was LittleAdversarialNetwork. However, the ad_net branch would consume a large amount of GPU memory, which has 1000 fully connected branch with 256 inputs and 1 outputs. How do you cope with this problem?

Best Regards.