Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Misplaced parenthesis in loss calculation? #1

Open
erikalu opened this issue Nov 16, 2017 · 0 comments
Open

Misplaced parenthesis in loss calculation? #1

erikalu opened this issue Nov 16, 2017 · 0 comments

Comments

@erikalu
Copy link

erikalu commented Nov 16, 2017

t = alpha * reshape((1-o(c_)).^gamma, [sz(1:2) 1 sz(4)]) .* (log(sum(ex,3)) - reshape(x(c_), [sz(1:2) 1 sz(4)])) + xmax;

It trains fine, but the loss increases. I think maybe the last closing parenthesis should be moved to the end, like so
t = alpha * reshape((1-o(c_)).^gamma, [sz(1:2) 1 sz(4)]) .* (log(sum(ex,3)) - reshape(x(c_), [sz(1:2) 1 sz(4)]) + xmax);

@erikalu erikalu changed the title Misplaced parenthesis in loss calculation Misplaced parenthesis in loss calculation? Dec 12, 2017
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant