Training Dataset Preprocessing Examples
Command examples used to preprocess training datasets. It will cut down on processing time if this is run and a static training dataset is used, instead of having to preprocess at all steps.
Make sure config files have been updated to contain all desired paths and parameterizations.
cd <path_to_SIT_FUSE>/SIT_FUSE/src/sit_fuse/datasets/
# Can be run outside of the repo via command line or in a script as well
# generate vectorized dataset
python3 sf_dataset.py -y <path_to_yaml>
# E.g. set <path_to_yaml> to ../config/model/emas_fire_dbn_multi_layer_pl.yaml
# generate tiled dataset
python3 sf_dataset_conv.py -y <path_to_yaml>
# E.g. set <path_to_yaml> to ../config/model/emas_fire_dbn_multi_layer_pl.yaml
Last updated