search

LikeLy-Journey / SegmenTron

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
Apache License 2.0
705 stars 162 forks source link

Multi-GPU Training Error #64

Open xiaodongyang opened 4 years ago

xiaodongyang commented 4 years ago

Thanks for the great work! I'm trying to use the multi-gpu training but got an error at line.

RuntimeError: Tensors must be CUDA and dense

xiaodongyang commented 4 years ago

I guess this error relates to pytorch version (1.4 I'm currently using). Could you please let me know what exact version did you use to be able to run the the multi-gpu training?

MegumiOuO commented 4 years ago

i have the same problem when using the multi-gpu training ,i use pytorch1.1

xiaodongyang commented 4 years ago

@Megumi-cs Thanks for the info. Did you figure out a solution?

jiawenhao2015 commented 4 years ago

~.~ waiting soluting....