tabensemb.model.AbstractNN.test_epoch#

method

AbstractNN.test_epoch(test_loader: DataLoader, **kwargs) → Tuple[ndarray, ndarray, float][source]#

Evaluate a torch.nn.Module model in a single epoch.

Parameters:

test_loader:: The DataLoader of the testing dataset.
**kwargs:: Parameters to train the model returned by AbstractModel._get_params(). It contains all arguments in AbstractModel._initial_values().

Returns:

np.ndarray: The prediction. Always a 2d torch.Tensor.
np.ndarray: The ground truth. Always a 2d torch.Tensor.
float: The default loss get_loss_fn() of the model on the testing dataset.