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.

Sign up for GitHub

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

Jump to bottom

lambda on test #126

Open
Riko0 opened this issue Sep 10, 2019 · 0 comments
Open

lambda on test #126

Riko0 opened this issue Sep 10, 2019 · 0 comments

Comments

@Riko0
Copy link

Riko0 commented Sep 10, 2019 •
edited
Loading

Does lambda in test have meaning?
usually its bigger than on train, but i guess it have no information in it, am i right?

I0906 19:50:07.181219 41380 solver.cpp:358] Iteration 2700, Testing net (#0)
I0906 19:50:07.997248 41380 solver.cpp:425] Test net output #0: accuracy/top-1 = 0.93375
I0906 19:50:07.997248 41380 solver.cpp:425] Test net output #1: lambda = 3.30186
I0906 19:50:07.998245 41380 solver.cpp:425] Test net output #2: softmax_loss = 0.216583 (* 1 = 0.216583 loss)
I0906 19:50:08.126904 41380 solver.cpp:243] Iteration 2700, loss = 0.465629
I0906 19:50:08.126904 41380 solver.cpp:259] Train net output #0: lambda = 3.08261
I0906 19:50:08.127900 41380 solver.cpp:259] Train net output #1: softmax_loss = 0.465629 (* 1 = 0.465629 loss)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Riko0