I meet a problem when run translate.py


(Patrick Liu) #1

I train the model without any change.
Then I input "python translate.py -model demo-model_acc_16.49_ppl_876.17_e12.p
t -src data/src-test.txt -output pred.txt -replace_unk -verbose "
It shows me that:“WARNING: -batch_size isn’t supported currently, we set it to 1 for now!”,"TypeError: float() argument must be a string or a number, not ‘torch.LongTensor’"
How to solve that problem?

(Guillaume Klein) #2


See here: