search

Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Apache License 2.0
2.86k stars 584 forks source link

multi-GPU Questions #10

Closed SuperWWF closed 5 years ago

SuperWWF commented 5 years ago

Hi, I want try a big batch_size so I need to multi-gpu, and I use the code about multi-gpu in train.py , But I found a problem in paraller.py

core/utils/parallel.py", line 136, in _worker
output = module(*(list(input) + target), **kwargs)
TypeError: can only concatenate list (not "tuple") to list

and I found some solutions in your References , link: https://github.com/zhanghang1989/PyTorch-Encoding/issues/116 but still some mistakes in validation outputs = self.model(image) And I use denseaspp model to train the data, And Could you give me some ideas about that. Thank you

Tramac commented 5 years ago

Hi, please try to change output = module(*(list(input) + target), **kwargs) to output = module(*(list(input) + [target]), **kwargs)