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

Feature: filter training data for maximal information entropy via flat multidimensional output-tensor histograms #169

Merged
merged 1 commit into from
Jul 8, 2024

Commits on Jul 8, 2024

  1. feat(cloud-microphysics): enable flat distribution

    This commit
    
    1. Adds cloud-microphysics/app/train-on-flat-distribution.f90,
       which takes the same command-line arguments as
       train-cloud-microphysics.f90 plus a new --bins argument that
       sets the number of bins to be used in each direction in phase
       space (i.e., output variable) when filtering training data so
       that each bin is occupied by at most one data point (i.e., one
       input/output tensor pairing).
    2. Works around a compiler bug that prevents the use of the new
       activation_factory_method function on the right-hand side of
       intrinsic assignments in inference_engine_t user-defined
       structure constructors.
    rouson committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    3625bf6 View commit details
    Browse the repository at this point in the history