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
Support receptive field search of CNN models. (TPAMI paper rf-next) #2439
base: master
Are you sure you want to change the base?
Conversation
Codecov ReportBase: 88.95% // Head: 88.79% // Decreases project coverage by
Additional details and impacted files@@ Coverage Diff @@
## master #2439 +/- ##
==========================================
- Coverage 88.95% 88.79% -0.16%
==========================================
Files 146 147 +1
Lines 8753 8721 -32
Branches 1474 1389 -85
==========================================
- Hits 7786 7744 -42
- Misses 725 735 +10
Partials 242 242
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report at Codecov. |
The weights and logs. link |
Motivation
Merging a general receptive field search method to mmseg.
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks TPAMI 2022)
RF-Next can improve the performance of many CNN networks on many tasks and has been merge in mmdet and mmcv.
more results on https://github.com/ShangHua-Gao/RF-mmdetection/tree/rfsearch/configs/rfnext
Modification
Add rfnext.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist