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

fine tuning pwc trained model #66

Closed
yoryory opened this issue Apr 29, 2019 · 2 comments
Closed

fine tuning pwc trained model #66

yoryory opened this issue Apr 29, 2019 · 2 comments

Comments

@yoryory
Copy link

yoryory commented Apr 29, 2019

hey,
can i use your training code to fine tuning not flownet model?
in my case i went fine tuning my trained pwc model on my data
thanks

@simonmeister
Copy link
Owner

simonmeister commented Apr 29, 2019

Depending on training mode, you would need to adapt some of the code in

https://github.com/simonmeister/UnFlow/blob/master/src/e2eflow/core/supervised.py
or
https://github.com/simonmeister/UnFlow/blob/master/src/e2eflow/core/unsupervised.py

All of the losses should work fine regardless of network and if I remember correctly the rest of the code outside of supervised.py and unsupervised.py shouldn't depend on the network. I may be wrong and there could be other changes required, but they would probably be minor.

@yoryory
Copy link
Author

yoryory commented Apr 30, 2019

thank you for your respond

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