-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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] Fix udp regress #1682
[Fix] Fix udp regress #1682
Conversation
Codecov ReportBase: 78.65% // Head: 78.65% // Decreases project coverage by
Additional details and impacted files@@ Coverage Diff @@
## dev-1.x #1682 +/- ##
===========================================
- Coverage 78.65% 78.65% -0.01%
===========================================
Files 203 203
Lines 11565 11568 +3
Branches 2019 2020 +1
===========================================
+ Hits 9097 9099 +2
Misses 2080 2080
- Partials 388 389 +1
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. |
@@ -83,7 +83,8 @@ | |||
in_channels=32, | |||
out_channels=3 * 17, | |||
deconv_out_channels=None, | |||
loss=dict(type='KeypointMSELoss', use_target_weight=True), | |||
loss=dict(type='CombinedTargetMSELoss', use_target_weight=True), | |||
print_acc_pose=False, |
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.
print_acc_pose=False, | |
compute_acc=False, |
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.
Another option is to get it from train_cfg
, like:
compute_acc = train_cfg.get('compute_acc', True)
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.
Agreed. I think put it into train_cfg
will be more reasonable.
Motivation
Fix loss in udp_regress.
Modification
BC-breaking (Optional)
Use cases (Optional)
Checklist
Before PR:
After PR: