-
Notifications
You must be signed in to change notification settings - Fork 212
Conversation
Codecov Report
@@ Coverage Diff @@
## master #230 +/- ##
==========================================
+ Coverage 86.49% 86.56% +0.06%
==========================================
Files 57 57
Lines 2829 2843 +14
==========================================
+ Hits 2447 2461 +14
Misses 382 382
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
flash/core/classification.py
Outdated
|
||
def to_metrics_format(self, x: torch.Tensor) -> torch.Tensor: | ||
if getattr(self.hparams, "multi_label", False): | ||
return F.sigmoid(x).int() |
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.
why int ? .round() might work better
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.
My bad, it was a bug.
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.
Looks good, see above small comments, meant to click comment rather than request changes haha
Hello @tchaton! Thanks for updating this PR.
Comment last updated at 2021-04-20 11:39:16 UTC |
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.
LGTM 😃
LGTM |
@tchaton Do we have a multi-label example of doing fine-tuning for merged features? |
What does this PR do?
This PR adds support for multi-label
Fixes #208
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃