You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I replaced the LightGBM model with LSTM in workflow_by_code.py but had trouble when running the code. The error is "Index Error: too many indices for tensor of dimension 0". Can someone help me with workflow_by_code-LSTM.py
I can run 'qrun benchmarks/LSTM/workflow_confid_lstm_Alpha158.yml' successfully.
Hi @JessieJie1998 , this error is caused by the fact that pytorch loader gives the model a batch (the last batch) with only one data sample, which results in error when calculating the loss. You could either fix the bug by adding drop_last=True argument to the train_loader and valid_loader in the file pytorch_lstm_ts.py, or you could wait for the merge of the related PR.
I replaced the LightGBM model with LSTM in workflow_by_code.py but had trouble when running the code. The error is "Index Error: too many indices for tensor of dimension 0". Can someone help me with workflow_by_code-LSTM.py
I can run 'qrun benchmarks/LSTM/workflow_confid_lstm_Alpha158.yml' successfully.
The text was updated successfully, but these errors were encountered: