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.

Sign up for GitHub

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

Jump to bottom

How to reproduce the paper result? #13

Open

sdsy888 opened this issue Feb 7, 2019 · 1 comment

sdsy888 commented Feb 7, 2019 •

edited

Loading

Hi, @aditya12agd5 @tomsherborne , thank you for publishing your source code.

Currently, I have already trained for 30 epochs (which is the default number of the epochs) and the results are:

Bleu_1: 0.665701
Bleu_2: 0.498210
Bleu_3: 0.361116
Bleu_4: 0.259780
METEOR: 0.222071
ROUGE_L: 0.494857
CIDEr: 0.636160

which is a long way to go to reach the performance in the paper.( I just run the code you provide without any modification. )

So, is there anything that I need to notice besides the code?

Thank you!

The text was updated successfully, but these errors were encountered:

danielabd commented Mar 9, 2019

I also be happy to get code for restore your results.
can we get it please?
@jyotianeja @aditya12agd5 @alexschwing

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment