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

Bump overlap to half the input samples #176

Merged
merged 1 commit into from Feb 20, 2023
Merged

Bump overlap to half the input samples #176

merged 1 commit into from Feb 20, 2023

Conversation

yetinam
Copy link
Member

@yetinam yetinam commented Feb 20, 2023

For the array annotation models, the default overlap is increased to half the number of input sample. This increases the stability of the predictions with respect to translation. However, this does not guarantee full translation invariance as the models themselves are not translation invariant.

Closes #167

@yetinam yetinam added the enhancement New feature or request label Feb 20, 2023
@yetinam yetinam added this to the v0.3 milestone Feb 20, 2023
@yetinam yetinam merged commit cb38d40 into main Feb 20, 2023
@yetinam yetinam deleted the phasenet_overlap branch February 20, 2023 17:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Suggest using half input length as the default overlap of picking models
1 participant