You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This repository is a benchmark: people are supposed to be able to run it repeatably for years to come...
I wonder if providing a VM image with guacamol + guacamol_baselines properly co-installed
wouldn't be the best solution in the long run.
The text was updated successfully, but these errors were encountered:
Hey @UnixJunkie, thanks for the suggestion. We provide a Dockerfile that allows you to recreate the environment in which the baselines were run, for guacamol_baselines this includes the exact versions of all dependencies.
For benchmarking your own models you only need to install guacamol from PyPI (version 0.5.4 will be released today)!
A pip installer for guacamol_baselines doesn't really make sense since baselines contains many implementations of baseline models, the underlying guacamol library is, however, pip installable.
This repository is a benchmark: people are supposed to be able to run it repeatably for years to come...
I wonder if providing a VM image with guacamol + guacamol_baselines properly co-installed
wouldn't be the best solution in the long run.
The text was updated successfully, but these errors were encountered: