nh.evaluation
- neuralhydrology.evaluation.get_tester(cfg: Config, run_dir: Path, period: str, init_model: bool) BaseTester
Get specific tester class objects depending on the model (head) type.
- Parameters:
cfg (Config) – The run configuration.
run_dir (Path) – Path to the run directory.
period ({'train', 'validation', 'test'}) – The period to evaluate.
init_model (bool) – If True, the model weights will be initialized with the checkpoint from the last available epoch in run_dir.
- Returns:
RegressionTester if the model head is ‘regression’. UncertaintyTester if the model head is one of {‘gmm’, ‘cmal’, ‘umal’} or if the evaluation is run in MC-Dropout mode.
- Return type: