Update example losses to bce- metrics/confusion_metrics.py by Frightera · Pull Request #18045 · keras-team/keras (original) (raw)

@Frightera

grasskin

@Frightera

grasskin

copybara-service bot pushed a commit that referenced this pull request

May 2, 2023

@tensorflower-gardener

Imported from GitHub PR #18045

I think it is better to use "binary_crossentropy" instead of "mse" as those metrics are for classification purposes. Copybara import of the project:

-- 0bf48b8 by Kaan Bıçakcı kaan.dvlpr@gmail.com:

Update example losses to binary_crossentropy

Merging this change closes #18045

FUTURE_COPYBARA_INTEGRATE_REVIEW=#18045 from Frightera:fix_metrics_loss 6dd4013 PiperOrigin-RevId: 528816084

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

[ Show hidden characters]({{ revealButtonHref }})