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.

Sign up for GitHub

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

Jump to bottom

use BaseDenseHead #2963

Merged
merged 4 commits into from
Jun 16, 2020
Merged

use BaseDenseHead #2963

merged 4 commits into from
Jun 16, 2020

Conversation

thangvubk
Copy link
Contributor

This is related to #1900. A BaseDenseHead is used to wrap train and test logics of dense heads, make them more flexible and easier to extend.
Here are some unit tests that I have performed on Faster R-CNN, RetinaNet, and RPN with R50-FPN:

Item Result
Simple test Reproduce model zoo results
Aug test Improved results compared to model zoo
Train (several iterations) Run normally

I do not have enough time and resource to rebenchmark the models.

@hellock hellock requested review from xvjiarui and yhcao6 June 9, 2020 14:07
yhcao6
yhcao6 reviewed Jun 11, 2020
View reviewed changes
Copy link
Collaborator

@yhcao6 yhcao6 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for your contribution. The code is well written but I have a little suggestion please check that.

mmdet/models/dense_heads/base_rpn_head.py Outdated Show resolved Hide resolved
@thangvubk thangvubk requested a review from yhcao6 June 12, 2020 05:25
@hellock hellock merged commit d28f394 into open-mmlab:master Jun 16, 2020
mike112223 pushed a commit to mike112223/mmdetection that referenced this pull request Aug 25, 2020
@thangvubk
use BaseDenseHead (open-mmlab#2963)
970c12f 
* use BaseDenseHead

* use RPNTestMixin in rpn heads

* use self(x) instead of self.__call__(x)

* use kwargs
FANGAreNotGnu pushed a commit to FANGAreNotGnu/mmdetection that referenced this pull request Oct 23, 2023
Update release instruction (open-mmlab#2963)
f326e46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@hellock hellock hellock approved these changes

@yhcao6 yhcao6 yhcao6 approved these changes

@xvjiarui xvjiarui Awaiting requested review from xvjiarui

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@thangvubk @hellock @yhcao6