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

question about forward_free() function #13

Closed
Sarah20187 opened this issue Dec 7, 2016 · 2 comments
Closed

question about forward_free() function #13

Sarah20187 opened this issue Dec 7, 2016 · 2 comments

Comments

@Sarah20187
Copy link

As torch has its own forward function, why use forward_free in net_te1?

@jzbontar
Copy link
Owner

forward_free is a memory optimized version of torch's default forward method. The idea is simple: if you don't need to compute gradients, you don't need to store the outputs of each layer.

Today, I would simply use https://github.com/fmassa/optimize-net, but this module did not exist when the mc-cnn code was written.

@Sarah20187
Copy link
Author

@jzbontar I found that in evaluation mode, forward_free() perform much better than optnet(set parameters to {mode='inference', inplace=false} )

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