Closed cjf9028 closed 5 years ago
Hi!
Thanks for the interest in our project. I need some more information in order to find out where that bug comes from. Just committed an issue template you can find here.
Could you please edit your message so as to conform to the new template so that I can more easily figure out what went wrong?
Are you able to run the usage commands from the README.md by following the exact instructions? Yes
Describe the bug A clear and concise description of what the bug is.
To Reproduce Steps to reproduce the behavior:
1 La DET DET 2 det 2 construcción NOUN NOUN 11 nsubj 3 de ADP ADP 5 adp 4 la DET DET 5 det
and use glove 6b 30d
Run this command python main.py --train-config config/train.config --decode-config config/decode.config
See error
Learning rate is set as: 0.02 Traceback (most recent call last): File "main.py", line 476, in train(train_data,decode,args) File "main.py", line 314, in train instance, data.HP_gpu) File "main.py", line 225, in batchify_with_label mask[idx, :seqlen] = torch.Tensor([1] * seqlen) TypeError: mul(): argument 'other' (position 1) must be Tensor, not list
OS: [Ubuntu 16.04] Python version [e.g. 2.7] Pytorch version [e.g. 0.3] Additional context Add any other context about the problem here.
It can be related to the PyTorch version you use. Which one is it? It should be 0.3.
oh i install wrong version after change version working
Learning rate is set as: 0.02 Traceback (most recent call last): File "main.py", line 476, in
train(train_data,decode,args)
File "main.py", line 314, in train
instance, data.HP_gpu)
File "main.py", line 225, in batchify_with_label
mask[idx, :seqlen] = torch.Tensor([1] * seqlen)
TypeError: mul(): argument 'other' (position 1) must be Tensor, not list
how to solve it