Skip to content
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

Compute loss on final val #5017

Merged
merged 1 commit into from
Sep 30, 2021
Merged

Compute loss on final val #5017

merged 1 commit into from
Sep 30, 2021

Conversation

glenn-jocher
Copy link
Member

@glenn-jocher glenn-jocher commented Sep 30, 2021

πŸ› οΈ PR Summary

Made with ❀️ by Ultralytics Actions

🌟 Summary

Enhanced model validation during training in YOLOv5.

πŸ“Š Key Changes

  • Added the compute_loss function as an argument to the validation step in the training pipeline.

🎯 Purpose & Impact

  • Purpose: To enable the calculation of loss on the validation dataset during training, which can help in understanding model performance and diagnosing issues.
  • Impact: This change may allow developers and researchers to obtain more detailed insights into how their model is performing during the train-eval cycle, potentially leading to better model tuning and improved performance.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant