Skip to content
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

Reproducing NME on test data #4

Closed
thomhert opened this issue Mar 8, 2021 · 2 comments
Closed

Reproducing NME on test data #4

thomhert opened this issue Mar 8, 2021 · 2 comments

Comments

@thomhert
Copy link

thomhert commented Mar 8, 2021

Hi
Thank you for sharing your codes.

I have downloaded one of the dataset (COFW) and tested using available pre-trained models (resnet18). The NME score that I got is 0.08758. If I multiply the score with 100%, it results in 8.758%.

Q: How to produce the same NME score as your paper? In the COFW, it is reported as 3.31%. Thank you.

@jhb86253817
Copy link
Owner

Hi, what's your PyTorch version? If it's over 1.6, there may be inconsistency for int tensor division, related to line 185 and 190 in functions.py. You can replace "max_ids/tmp_width" by "torch.floor(max_ids/tmp_width)"

@thomhert
Copy link
Author

thomhert commented Mar 9, 2021

My PyTorch version is 1.7. I managed to get the same results by changing line 185 and 190 as you suggested. Thank you!

@thomhert thomhert closed this as completed Mar 9, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants