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
2.8k stars 581 forks source link

the deeplabv3 plus model could not be trained. #118

Open Readon opened 4 years ago

Readon commented 4 years ago

When I tried to train the deeplabv3 model by: python train.py --model deeplabv3_plus --backbone resnet50 --dataset ade20k --lr 0.0001 --epochs 50 it reports that: model = Xception65(**kwargs) TypeError: init() got a unexpected keyword argument 'jpu'

After tracing the code, it seems that the DeepLabV3Plus class is not inherit from the SegBaseModel which implement the jpu parameter support. Is that the essence of DeepLabV3Plus which could not support the jpu?

atangmao commented 2 years ago

I met the same problem, how did you slove it?

bbbts commented 2 weeks ago

When I tried to train the deeplabv3 model by: python train.py --model deeplabv3_plus --backbone resnet50 --dataset ade20k --lr 0.0001 --epochs 50 it reports that: model = Xception65(kwargs) TypeError: init**() got a unexpected keyword argument 'jpu'

After tracing the code, it seems that the DeepLabV3Plus class is not inherit from the SegBaseModel which implement the jpu parameter support. Is that the essence of DeepLabV3Plus which could not support the jpu? @atangmao @Readon I'm having the same issue. Were you able to solve it?