Open
Description
Hello,
I encountered an issue when running the example provided on the page using the following command:
python main.py --cfg configs/Mamba/peptides-func-EX.yaml wandb.use False
After the preprocessing phase was completed and just as the first training epoch was about to start, I received the following error:
Python
Traceback (most recent call last):
File "/home/user/Documents/Graph-Mamba/main.py", line 175, in <module>
train_dictcfg.train.mode)
File "/home/user/Documents/Graph-Mamba/graphgps/logger.py", line 245, in write_epoch
task_stats = self.classification_multilabel()
File "/home/user/Documents/Graph-Mamba/graphgps/logger.py", line 146, in classification_multilabel
'accuracy': reformat(acc(pred_score, true)),
File "/home/user/Documents/Graph-Mamba/graphgps/metric_wrapper.py", line 323, in __call__
return self.compute(preds, target)
File "/home/user/Documents/Graph-Mamba/graphgps/metric_wrapper.py", line 311, in compute
x = torch.stack(metric_val) # PyTorch<=1.9
RuntimeError: stack expects a non-empty TensorList
For comparison, I also ran mnist-EX.yaml
and peptides-struct-EX.yaml
. Both of these scripts executed as expected without any issues. This leads me to believe that the issue is not related to my installation of the conda environment and all the packages.
Any guidance or assistance would be greatly appreciated.
Thank you.
Metadata
Metadata
Assignees
Labels
No labels