Results
14
comments of
Hang Zhao
Check out sceneparsing/visualizationCode/
We use only one channel to encode the 150 labels. For visualization, we use 3 channels.
@AaronLeong I am also using 4 gpus, here is the command I used, can you help to check? Thanks! ``` python main.py --batch_size 64 --dataset lsun --adv_loss hinge --version biggan_lsun...
@jcpeterson 12GB, the batch size fits, so it should not matter