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.

Sign up for GitHub

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

Jump to bottom

Using one training to make multiple guesses #61

Open

ardunn opened this issue Jan 16, 2019 · 1 comment

Labels

major enhancement v1.1

Collaborator

ardunn commented Jan 16, 2019

It would be cool to have:

set an arg retrain_interval, and it will only retrain the model(s?, for bootstrapping) that often
during batch mode, use the same model to make multiple predictions without compromising guess accuracy

ardunn added the major enhancement label

ardunn added the v1.1 label

Collaborator Author

ardunn commented Jul 31, 2020

make sure this would work with batches as well

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment