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

about bbox regression #35

Open
foralliance opened this issue Dec 17, 2018 · 1 comment
Open

about bbox regression #35

foralliance opened this issue Dec 17, 2018 · 1 comment

Comments

@foralliance
Copy link

foralliance commented Dec 17, 2018

@louis-she HI
在利用anchors坐标网络预测的偏移量得到最终box坐标时,都会引入一个参数variances.但在您的代码中,并未看到此参数.

x = (predictions[:, 0] * anchors[:, 2] + anchors[:, 0])
y = (predictions[:, 1] * anchors[:, 3] + anchors[:, 1])
w = (torch.exp(predictions[:, 2]) * anchors[:, 2])
h = (torch.exp(predictions[:, 3]) * anchors[:, 3])

bounding_boxes = torch.stack((x, y, w, h), dim=1).cpu().data.numpy()  #(200,4)
bounding_boxes = change_coordinate_inv(bounding_boxes)
@louis-she
Copy link
Owner

louis-she commented Dec 17, 2018

是的,在SSD源码里面有这个参数,但我没加因为论文中没有提到,因为我感觉这种参数应该是可以学习到的。

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

2 participants