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

which type of mxnet do you use? #3

Open
wjzln57 opened this issue May 14, 2018 · 3 comments
Open

which type of mxnet do you use? #3

wjzln57 opened this issue May 14, 2018 · 3 comments

Comments

@wjzln57
Copy link

wjzln57 commented May 14, 2018

I used mxnet-cu80 to train mobilefacenet model. However there are many [lfw][4000] Accuracy-Flip: 0.50000+-0.0000 during the training, and the log is different yours. Did you use mxnet-cu90 to train you model?
@moli232777144
Copy link
Owner

I've tried mxnet-cu80 and mxnet-cu90. It's all true。

@wjzln57
Copy link
Author

wjzln57 commented May 14, 2018

Your log was printed by mxnet-cu80 or mxnet-cu90? I have trainded several models with the wd=0.005, and the results were all bad. I just changed the wd to 0.00004.

@moli232777144
Copy link
Owner

mxnet-cu80 log：Speed: 520+ samples/sec
mxnet-cu90 log：Speed: 580+ samples/sec

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
2 participants
@wjzln57 @moli232777144