Skip to content

Conversation

aismlv
Copy link

@aismlv aismlv commented Oct 19, 2022

The current value of 1e-6 could be too high for larger datasets and could lead to model performance degradation. The original value was set here.

This PR sets the value to a lower 1.1920928955078125e-09 that comes from np.finfo(np.float32).eps / 100 in line with other clipping constants in the project.

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