CDAN
CDAN copied to clipboard
Cannot train pytorch version on multi-gpu
When trained on multi-gpu, the transfer loss (CDAN + Entropy loss) is very low and the test accuracy alway decreases. Dataset: visda2017 tested on Ubuntu 18.04, Pytorch version: 1.2.0 / 1.4.0, GPU: GTX 1080 / RTX 2080Ti
我也会出现这样的情况