Focal loss c++ implementation #1807
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 10 commits
August 9, 2021 14:26
sagol
reviewed
Aug 13, 2021
| curApprox += approxDelta[k]; | ||
| } | ||
| const float w = hasWeight ? weight[k] : 1; | ||
| double FocalAlpha = 0.75; |
There was a problem hiding this comment.
It is necessary to pass these parameters into the metric somehow.
There was a problem hiding this comment.
I'd better wait for maintainers' advice on how to do it in the most correct way(probably in the way I did it with loss params)
sagol
reviewed
Aug 13, 2021
| } | ||
| const float w = hasWeight ? weight[k] : 1; | ||
| double FocalAlpha = 0.75; | ||
| double FocalGamma = 2; |
|
@arcadia-devtools Ship it! |
|
CLA already signed |
|
@arcadia-devtools Ship it! |
|
thanks your great job. |
|
Thank you for your contribution. Sorry for the long wait. I've merged this PR (the original author is preserved). |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I hereby agree to the terms of the CLA available at [https://yandex.ru/legal/cla/?lang=en].
Adds a focal loss CPU implementation. Focal loss is widely used in classification tasks with highly imbalanced data.
Details can be found here:
https://arxiv.org/abs/1708.02002 - original paper
https://paperswithcode.com/method/focal-loss - 216 papers used it.
Possible problems:
"loss_function": "Focal:focal_alpha=0.75;focal_gamma=2.0"