Skip to content

Eval

Main evaluation script.

evaluate(cfg) #

Evaluates given checkpoint on a datamodule testset.

This method is wrapped in optional @task_wrapper decorator, that controls the behavior during failure. Useful for multiruns, saving info about the crash, etc.

Parameters:

Name Type Description Default
cfg DictConfig

DictConfig configuration composed by Hydra.

 required

Returns:

Type Description
tuple[dict[str, Any], dict[str, Any]]

tuple[dict, dict] with metrics and dict with all instantiated objects.
Source code in src/eval.py 
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
@task_wrapper
def evaluate(cfg: DictConfig) -> tuple[dict[str, Any], dict[str, Any]]:
    """Evaluates given checkpoint on a datamodule testset.

    This method is wrapped in optional @task_wrapper decorator, that controls the behavior during
    failure. Useful for multiruns, saving info about the crash, etc.

    Args:
        cfg: DictConfig configuration composed by Hydra.

    Returns:
        tuple[dict, dict] with metrics and dict with all instantiated objects.
    """
    assert cfg.ckpt_path

    log.info(f"Instantiating datamodule <{cfg.data._target_}>")
    datamodule: LightningDataModule = hydra.utils.instantiate(cfg.data)

    log.info(f"Instantiating model <{cfg.model._target_}>")
    model: LightningModule = hydra.utils.instantiate(cfg.model)

    if cfg.get("model_compile", False):
        log.info("Compiling model...")
        torch.compile(model)

    log.info("Instantiating loggers...")
    logger: list[Logger] = instantiate_loggers(cfg.get("logger"))

    log.info(f"Instantiating trainer <{cfg.trainer._target_}>")
    trainer: Trainer = hydra.utils.instantiate(cfg.trainer, logger=logger)

    object_dict = {
        "cfg": cfg,
        "datamodule": datamodule,
        "model": model,
        "logger": logger,
        "trainer": trainer,
    }

    if logger:
        log.info("Logging hyperparameters!")
        log_hyperparameters(object_dict)

    log.info("Starting testing!")
    trainer.test(model=model, datamodule=datamodule, ckpt_path=cfg.ckpt_path)

    # for predictions use trainer.predict(...)
    # predictions = trainer.predict(model=model, dataloaders=dataloaders, ckpt_path=cfg.ckpt_path)

    metric_dict = trainer.callback_metrics

    return metric_dict, object_dict

main(cfg) #

Main entry point for evaluation.

:param cfg: DictConfig configuration composed by Hydra.

Source code in src/eval.py 
78
79
80
81
82
83
84
85
86
87
88
@hydra.main(version_base="1.3", config_path="../configs", config_name="eval.yaml")
def main(cfg: DictConfig) -> None:
    """Main entry point for evaluation.

    :param cfg: DictConfig configuration composed by Hydra.
    """
    # apply extra utilities
    # (e.g. ask for tags if none are provided in cfg, print cfg tree, etc.)
    extras(cfg)

    evaluate(cfg)