search

Li-Chongyi / Zero-DCE

Zero-DCE code and model
774 stars 187 forks source link

How to use multi-GPU training? #16

Open CGguy opened 3 years ago

Siddharth-Shrivastava7 commented 3 years ago

You could replace DCE_net = model.enhance_net_nopool().cuda() in train file by DCE_net = nn.DataParallel(model.enhance_net_nopool()).cuda()

Li-Chongyi commented 3 years ago

that’s correct. Thanks!

发自我的iPhone

在 2020年12月25日，下午3:36，Siddharth Shrivastava notifications@github.com 写道：

 You could replace DCE_net = model.enhance_net_nopool().cuda() in train file by DCE_net = nn.DataParallel(model.enhance_net_nopool()).cuda()

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.