Reagan1311 / DABNet

Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)
https://github.com/Reagan1311/DABNet
MIT License
140 stars 36 forks source link

Hi, I have got some problems about train.py. #37

Closed shiweigao closed 4 years ago

shiweigao commented 4 years ago

I found that the names of the pictures in train_list.txt do not match the cityscapes, like "cologne_000000_000019_gtFine_labelTrainIds.png" and "cologne_000000_000019_gtFine_labelIds.png". After the change, the error is reported as follows: Traceback (most recent call last): File "train.py", line 314, in train_model(args) File "train.py", line 217, in train_model lossTr, lr = train(args, trainLoader, model, criteria, optimizer, epoch) File "train.py", line 81, in train loss = criterion(output, labels) File "/home/uber/anaconda3/envs/DABNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) File "/home/uber/GraduateWork/2020/DABNet/DABNet-master/utils/loss.py", line 81, in forward index = mask_prob.argsort() File "/home/uber/anaconda3/envs/DABNet/lib/python3.6/site-packages/torch/tensor.py", line 248, in argsort return torch.argsort(self, dim, descending) File "/home/uber/anaconda3/envs/DABNet/lib/python3.6/site-packages/torch/functional.py", line 651, in argsort return torch.sort(input, -1, descending)[1] RuntimeError: merge_sort: failed to synchronize: device-side assert triggered

Could I get some help from you?

Reagan1311 commented 4 years ago

please refer to #34, hope this helps.

shiweigao commented 4 years ago

thx!