-
Notifications
You must be signed in to change notification settings - Fork 382
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
fix: Fixed LinkNet target & loss computation #670
Conversation
Codecov Report
@@ Coverage Diff @@
## main #670 +/- ##
==========================================
+ Coverage 96.17% 96.26% +0.08%
==========================================
Files 117 117
Lines 4472 4467 -5
==========================================
- Hits 4301 4300 -1
+ Misses 171 167 -4
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, but why do you remove the focal loss ?
It was introducing an asymetry in model API, and we added it because we were having bad performances with LinkNet initially. So I figured, it's better to start again simple, make it work and then if we decide that all segmentation models need it, we'll reintroduce it 👍 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks!
This PR introduces the following modifications:
edge_mask
buildingseg_target
for PyTorch (was built as channels last)Any feedback is welcome!