-
Notifications
You must be signed in to change notification settings - Fork 52
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
How does it work? #6
Comments
Actually I haven't get any gain for now. The result on face detection task of using default setting (alpha=0.25, gamma=2) is just similar with that of using |
@ScienceFans I've implement focal loss for SSD object detection framework. In my case, it's worsen than OHEM, but my friend get higher precision using it in semantic segmentation. The author used it in object detection with a self-created network similar to SSD. Although the performance is amazing, it is contributed by both larger input size and more anchor boxes. It's doubtful why they did not prove its effectiveness with a prevailed pipeline, and most likely the problem is in implementation details. Hope to see your further update and discussion. |
@Johnson-yue @XiaoyanLi1 |
@ScienceFans |
@XiaoyanLi1 I also tried focal loss with SSD, it's worse than OHEM.Do you have any update? |
@bailvwangzi The mAP under the best setting I've tried is still lower than OHEM. Considering the computation cost, I've stopped my experiment. The only conclusion is that the ratio (lambda) between classification loss and regression loss is important. Hyper-parameters I've tried are
|
Hi,sciencefans:
thank you for sharing your code , and I want to know is the Focal Loss work well?? How much improve than before?
The text was updated successfully, but these errors were encountered: