Skip to contents

Pre-process data for U-Net

Source: R/prep_unet.R
prep_unet.Rd

Creates numpy arrays ready for fitting in U-Net. Result files are placed in <site>/unet/<model>.

Usage

prep_unet(model, resources = NULL, local = FALSE, trap = TRUE, comment = NULL)

Arguments

model

The model name, which is also the name of a .yml parameter file in the pars directory. This file must contain the following:

  • year: the year to fit

  • orthos: portable names of all orthophotos to include

  • patch: size in pixels

  • depth: number of of downsampling stages

  • classes: vector of target classes

  • holdout: percent of data to hold out for validation

resources

Slurm launch resources. See launch. These take priority over the function's defaults.

local

If TRUE, run locally; otherwise, spawn a batch run on Unity

trap

If TRUE, trap errors in local mode; if FALSE, use normal R error handling. Use this for debugging. If you get unrecovered errors, the job won't be added to the jobs database. Has no effect if local = FALSE.

comment

Optional slurmcollie comment

Details

Try this to test: prep_unet('unet01', local = TRUE)