sup3r.utilities.loss_metrics.PhysicsBasedLoss

class PhysicsBasedLoss(input_features='all')

Bases: Loss

Base class for physics-based loss metrics. This is meant to be used as a base class for loss metrics that require specific input features.

Initialize the loss with given input features

Parameters:

input_features (list | str) – List of input features that the loss metric will be calculated on. This is meant to be used for physics-based loss metrics that require specific input features. If ‘all’, the loss will be calculated on all features. Otherwise, the loss will be calculated on the features specified in the list. The order of features in the list will be checked to determine the order of features in the input tensors.

Methods

call(y_true, y_pred)	Invokes the Loss instance.
from_config(config)	Instantiates a Loss from its config (output of get_config()).
get_config()	Returns the config dictionary for a Loss instance.

__call__(y_true, y_pred, sample_weight=None)

Invokes the Loss instance.

Args:

y_true: Ground truth values. shape = [batch_size, d0, .. dN],

except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]

y_pred: The predicted values. shape = [batch_size, d0, .. dN] sample_weight: Optional sample_weight acts as a coefficient for

the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each loss element of y_pred is scaled by the corresponding value of sample_weight. (Note on`dN-1`: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns:

Weighted loss float Tensor. If reduction is NONE, this has

shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1 because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises:

ValueError: If the shape of sample_weight is invalid.

abstract call(y_true, y_pred)

Invokes the Loss instance.

Args:

y_true: Ground truth values. shape = [batch_size, d0, .. dN],

except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]

y_pred: The predicted values. shape = [batch_size, d0, .. dN]

Returns:

Loss values with the shape [batch_size, d0, .. dN-1].

classmethod from_config(config)

Instantiates a Loss from its config (output of get_config()).

Args:

config: Output of get_config().

Returns:

A Loss instance.

get_config()

Returns the config dictionary for a Loss instance.