Skip to content

Latest commit

 

History

History
24 lines (18 loc) · 1.01 KB

PRETRAINED_EMULATORS.md

File metadata and controls

24 lines (18 loc) · 1.01 KB

Pretrained Emulators

The subdirectory emulationResults/trainedParameters stores pretrained emulation parameters. The commands below show how to use these parameters to make predictions on the test data.

TwistingCube

Predictions can be run as follows:

python -m main --mode="evaluate" --data_path="TwistingBeam" --dir_label="_preTrained" --trained_params_dir="emulationResults/trainedParameters/TwistingBeam/"

Liver

Predictions can be run as follows:

python -m main --mode="evaluate" --data_path="Liver" --dir_label="_preTrained" --trained_params_dir="emulationResults/trainedParameters/Liver/"

LeftVentricle

Predictions can be run as follows:

python -m main --mode="evaluate" --data_path="LeftVentricle" --dir_label="_preTrained" --trained_params_dir="emulationResults/trainedParameters/LeftVentricle/"

Note, as discussed in the README, this is a slightly different version of the LeftVentricle data that was used in the paper.