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
Where are the hooks among classes? #19
Comments
See this code, the mmcv runner hooks all these components. |
So they are processed in order right? and what if I just want to run |
In fact, ZeroShotTwoStageDetector is composed of Backbone, BackgroundAwareRPNHead, SharedFCSemanticBBoxHead and SemanticFCNMaskHead. Just like mask rcnn is also composed of similar modules. |
"In fact, ZeroShotTwoStageDetector is composed of Backbone, BackgroundAwareRPNHead, SharedFCSemanticBBoxHead and SemanticFCNMaskHead." |
Please See:
|
Oh we don't need to directly call |
Yes, we don't need to directly call BackgroundAwareRPNHead, SharedFCSemanticBBoxHead. We pass the class name and the corresponding parameters from config file into zero_shot_two_stage, the the builder uses the class name like |
You're awesome. I've got it. I was looking at the |
|
In your config file for train 65, I can see a class order like this:
ZeroShotMaskRCNN
->BackgroundAwareRPNHead
->SharedFCSemanticBBoxHead
- >SemanticFCNMaskHead
They are classes located in
mmdet/models
, where are the hook functions that connect among those classes?The text was updated successfully, but these errors were encountered: