-
Notifications
You must be signed in to change notification settings - Fork 1
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
Problems with training #1
Comments
It's high variance due to the small data regime and noise from pose estimation. Especially, the "Coat" condition has the highest variance. |
Did you use hyperparameter as same as the common.py setting default when running experiments, I really confused about the result I trained on a V-100. The mean accuracy is NM#5-6: 0.8499, BG#1-2: 0.7028, CL#1-2:0.6968 |
Yes. We use the same default parameters as common.py. For BG and CL, the evaluation has very high variance but NM should not see much difference. |
Dear the authors:
I downloaded your code and trained it with 2 GTX1080Ti according to your readme document. But the training effect is much worse. Is there anything wrong with me? Attached is the training results.
NM#5-6 0.937374 0.935354 0.948000 0.942424 ... 0.950 0.948 0.912 0.939596
BG#1-2 0.809091 0.829293 0.826263 0.835714 ... 0.816 0.840 0.787 0.811113
CL#1-2 0.780000 0.810000 0.819000 0.806122 ... 0.827 0.817 0.800 0.808069
The text was updated successfully, but these errors were encountered: