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.

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

请问作者,loss中对x,y使用的交叉熵是否应为squared loss? #21

Open
ld909 opened this issue Dec 12, 2018 · 0 comments
Open

Comments

@ld909
Copy link

ld909 commented Dec 12, 2018

yolo v3 于2.1. Bounding Box Prediction中对xywh使用的loss进行了说明:

During training we use sum of squared error loss.

但在作者的实现中,对wh使用的确实是squared loss,但xy实现使用交叉熵,代码如下:

xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[..., 0:2],
                                                               from_logits=True)

所以请教作者为何这样实现?
谢谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant