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

the meaning of "split_batch"? #28

Open
Grassyue opened this issue Jul 25, 2019 · 4 comments
Open

the meaning of "split_batch"? #28

Grassyue opened this issue Jul 25, 2019 · 4 comments

Comments

@Grassyue
Copy link

Grassyue commented Jul 25, 2019

Hi, thank you for your sharing and sorry to bother you, i am a new guy in super-resolution, can you explain the meaning of "split_batch" in the code? thank you sooo much!

@Grassyue Grassyue reopened this Jul 25, 2019
@Grassyue Grassyue changed the title the meaning of "use_cl"? the meaning of "split_batch"? Jul 25, 2019
@Paper99
Copy link
Owner

Paper99 commented Jul 26, 2019

Each batch will first split into N (depending on the value of split_batch) sub-batches before feeding to the network. The larger split_batch will lead to less GPU memory usage during training.

@Grassyue
Copy link
Author

Thanks for your reply,but why not directly set the batch size to a small number? what is the difference?

@Paper99
Copy link
Owner

Paper99 commented Jul 29, 2019

When you set a large batchsize, the option split_batch make it possible to update the parameters only once.

@DamperHa
Copy link

When I use the option split_batch, the accuracy was much worse on the test set, what is the reason for this?

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

3 participants