-
Notifications
You must be signed in to change notification settings - Fork 9.4k
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
CenterNet(Objects as points) #4602
Conversation
# Conflicts: # mmdet/models/dense_heads/__init__.py # mmdet/models/detectors/__init__.py
Thanks for your contribution! |
The general structure of the code looks good to me. |
# Conflicts: # mmdet/__init__.py # mmdet/models/dense_heads/__init__.py # mmdet/models/necks/__init__.py # tests/test_models/test_heads.py
@kellenf I don't know if it's appropriate to ask question here. Really exceting about this work! But I think there is may a bug here. I notice when generating the box target in And when the dataset get multi scale and set the What I think it should feed
|
@igo312 Thanks for your attention. In the default configuration, width_ratio or height_ratio is always equal to 4, and multi-scale training is not supported by default, so there is no problem. But if you consider multi-scale training, there are hidden dangers. The best way is to replace |
@hhaAndroid Well I don't really understand what's the difference between The problem should be when a batch get difference scale of image, using the index 0 of |
|
yeah...You are right, Anyway, really thanks for your response! |
Compared to the source code, we refer to CenterNet-Better, and make the following changes:
Due to complex data enhancement, we find that the performance is unstable and may fluctuate by about 0.4 mAP. mAP 29.4 ~ 29.8 is acceptable in ResNet18-DCN.
DLANet source code will be released in other PRs.