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

I want to know how to train this net #20

Open
tzw-1998 opened this issue Nov 9, 2017 · 8 comments
Open

I want to know how to train this net #20

tzw-1998 opened this issue Nov 9, 2017 · 8 comments

Comments

@tzw-1998
Copy link

tzw-1998 commented Nov 9, 2017

No description provided.

@mingchuan123
Copy link

Me too.

@bertinetto
Copy link
Collaborator

bertinetto commented Nov 11, 2017

This version uses a matconvnet-pretrained network.
You can train new models using the code from the conv5 baseline of CFNet

However, since the model is fully specified in this TensorFlow project, it shouldn't be too much work to add a logistic loss and the training code.

If you can wait though, we might come up with a PyTorch (better) version at some point next year.

@ahkarami
Copy link

+1 for PyTorch Code

@omkar13
Copy link

omkar13 commented Feb 27, 2018

+1 for PyTorch code

@bertinetto
Copy link
Collaborator

I have actually finished with the pytorch version a couple of weeks ago but it's a bit behind the original implementation performance.

I might try and release it, perhaps people can help levelling the performance?

@ahkarami
Copy link

Yes, if you release the PyTorch version maybe we can help you to increase its performance.

@ahkarami
Copy link

Dear @bertinetto,
Have you released the PyTorch version of the project?

@serkansulun
Copy link

Dear Luca,
Can you release the PyTorch version? I'd be happy to work on it.

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

6 participants