seq2seq.pytorch
seq2seq.pytorch copied to clipboard
eladhoffer
Sequence-to-Sequence learning using PyTorch
Hi Elad, I am using your code for my task. I face an error related to **ModuleNotFoundError: No module named 'seq2seq.tools.utils.log'.** I already executed script **python setup.py develop** but after...
When running main.py, I get the following error: ```Traceback (most recent call last): File "main.py", line 15, in from seq2seq import models, datasets File "seq2seq.pytorch\seq2seq\models\__init__.py", line 1, in from .transformer...
Hi In the file of modules/attention.py, the class MultiHeadAttention(nn.MultiheadAttention) is reported an error: class MultiHeadAttention(nn.MultiheadAttention): AttributeError: module 'torch.nn' has no attribute 'MultiheadAttention' I use the pytorch=0.4.1. Is there any version...
In this line, https://github.com/eladhoffer/seq2seq.pytorch/blob/348276b2fcc5a60352b3dccaae7102666dbbd4ac/seq2seq/tools/beam_search.py#L216, the decrease of num_hyp will increase the value of k, which then leads to the out-of-bounds for the words[idx][k], I don't know why you use num_hyp?
Hi. Please i would like to know how to train train these models. When i ran train_en_de.sh, i get errors: Traceback (most recent call last): File "/media/vivien/A/NEW-SMT/seq2seq.pytorch-master/main.py", line 15, in...
Dear @eladhoffer, Do you have any experience how to productionize this seq2seq model in high-performant way (like serve it using REST API)? Thanks
Based on issues, this project is on progress and I would like to develop more. However, It seems like you uses same seq2seq base model, not for the conv s2s...
Hi are the ByteNet and Convolutional things here working? have they been tested? seems like since some refactoring they are broken, but i'm wondering if the code there has been...
