-
-
Notifications
You must be signed in to change notification settings - Fork 16.1k
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
Label smoothing in training option #2332
Comments
@ptran1203 we do have a class label smoothing option, though we couldn't get better performance with it. You can experiment with it here, and let us know if it helps you! I would also start with very small eps, i.e. 0.01 maybe for your experiments. Lines 99 to 101 in fab5085
|
@glenn-jocher Thank you, I see, I will do some experiments with this. |
@glenn-jocher , I saw hyp params already attached in the model and it can be easily obtained via |
Yes PR is good idea!
On Mon, Mar 1, 2021 at 7:44 PM Phat Tran ***@***.***> wrote:
@glenn-jocher <https://github.com/glenn-jocher> , I saw hyp params
already attached in the model and it can be easily obtained via h.get('label_smoothing_eps',
0.0)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#2332 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGMXEGLXLQNEPCOAG32XWL3TBRNJTANCNFSM4YN3N5MQ>
.
--
<https://www.ultralytics.com/>
*Glenn Jocher*Founder & CEO, Ultralytics LLC
+1 301 237 6695
<https://www.facebook.com/ultralytics>
<https://www.twitter.com/ultralytics>
<https://www.youtube.com/ultralytics>
<https://www.github.com/ultralytics>
<https://www.linkedin.com/company/ultralytics>
<https://www.instagram.com/ultralytics>
<https://contact.ultralytics.com/>
|
@ptran1203 Did you obtain better mAP results with label smoothing? |
Hi, I could not find any questions about label smoothing, so I wonder if there is
label smoothing
option in the training script?I think it would be useful, as the authors (from this paper) demonstrated the performance boost.
The text was updated successfully, but these errors were encountered: