New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
pytorch-seq2seq slower than OpenNMT-py #27
Comments
@kylegao91 Changed Things that made a big difference:
|
@Deepblue129 Thanks a lot! I will try the ideas. |
@Deepblue129 Regarding the 3rd point, your code ignored the condition |
If speed is essential, why not step up to Python 3.6 or to pypy? Both are faster that Python 2.7. |
@cclauss It's like, doing that would speed up an O(N^2) sorting algorithm, but it's still O(N^2) instead of O(Nlog(N))... |
Benchmarked the two implementations using WMT's newstest2013 from German to English. See training logs in the gist. Despite accuracy differences, pytorch-seq2seq is 10 times slower than OpenNMT.py.
The text was updated successfully, but these errors were encountered: