search

xiaoyufenfei / Efficient-Segmentation-Networks

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
MIT License
923 stars 164 forks source link

ESNet: Error after 161 iterations #7

Open shifangtian opened 4 years ago

shifangtian commented 4 years ago

Such like this: =====> epoch[161/300] iter: (526/1329) cur_lr: 0.000251 loss: 0.445 time:0.67 =====> epoch[161/300] iter: (527/1329) cur_lr: 0.000251 loss: 0.196 time:0.58 Traceback (most recent call last): File "D:/my/torch-gpu/Efficient-Segmentation-Networks/Efficient-Segmentation-Networks/train.py", line 398, in train_model(args) File "D:/my/torch-gpu/Efficient-Segmentation-Networks/Efficient-Segmentation-Networks/train.py", line 215, in train_model lossTr, lr = train(args, trainLoader, model, criteria, optimizer, epoch) File "D:/my/torch-gpu/Efficient-Segmentation-Networks/Efficient-Segmentation-Networks/train.py", line 329, in train loss.backward() File "D:\deeplearning\anaconda\envs\torch-gpu\lib\site-packages\torch\tensor.py", line 107, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "D:\deeplearning\anaconda\envs\torch-gpu\lib\site-packages\torch\autograd__init.py", line 87, in backward grad_tensors = _make_grads(tensors, grad_tensors) File "D:\deeplearning\anaconda\envs\torch-gpu\lib\site-packages\torch\autograd\init__.py", line 28, in _make_grads raise RuntimeError("grad can be implicitly created only for scalar outputs") RuntimeError: grad can be implicitly created only for scalar outputs

xiaoyufenfei commented 4 years ago

Can you provide more information? you solved it?

shifangtian commented 4 years ago

Can you provide more information? you solved it?

no,it still exists.my cuda is 9.0 ,gpu:gtx1660,dataset:cityscapes,batchsize:2

xiaoyufenfei commented 4 years ago

sorry, I have check, no any problem