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

five extra target variables (TPAMI论文中提到的额外添加的五个输出参数在code中的具体位置) #42

Open
Easonsen opened this issue Feb 24, 2021 · 2 comments

Comments

@Easonsen
Copy link

您好!您论文中提到了只是在faster RCNN head上加了5个额外的输出参数,请问在代码中是如何体现这5个额外参数的呢?(很抱歉打扰您了)

@Easonsen
Copy link
Author

Easonsen commented Feb 24, 2021

在gliding_vertex/maskrcnn_benchmark/modeling/roi_heads/box_head/roi_box_predictors.py中

NOTE Mingtao
@registry.ROI_BOX_PREDICTOR.register("FPNRatioPredictor")
@registry.ROI_BOX_PREDICTOR.register("RatioPredictor")
class FPNRatioPredictor(nn.Module):

这个类是不是就是您定义的输出呢?
bbox_pred就是文中的 ‘horizontal bounding box (x, y, w, h)’

而fix_pred就是文中的 'four variables (alpha1, alpha2, alpha3, alpha4) characterizing the oriented bounding box'

而ratio_pred就是文中的 'obliquity factor r that indicates whether the object is nearly horizontal or not'

如有错误,望您指正。

@Easonsen Easonsen changed the title five extra target variables five extra target variables (TPAMI论文中提到的额外添加的五个输出参数在code中的具体位置) Feb 24, 2021
@qimw
Copy link
Collaborator

qimw commented Apr 1, 2021

是的, fix 可以看作是 gliding_vertex 的一个alias

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