Classification
Classification loss functions.
-
nabla.nn.losses.classification.cross_entropy_loss(logits, targets, axis=-1)[source]
Compute cross-entropy loss between logits and targets.
- Parameters:
logits (Array) – Raw model outputs (before softmax) [batch_size, num_classes]
targets (Array) – One-hot encoded targets [batch_size, num_classes]
axis (int) – Axis along which to compute softmax
- Returns:
Scalar loss value
- Return type:
Array
-
nabla.nn.losses.classification.sparse_cross_entropy_loss(logits, targets, axis=-1)[source]
Compute cross-entropy loss with integer targets.
- Parameters:
logits (Array) – Raw model outputs [batch_size, num_classes]
targets (Array) – Integer class indices [batch_size]
axis (int) – Axis along which to compute softmax
- Returns:
Scalar loss value
- Return type:
Array
-
nabla.nn.losses.classification.binary_cross_entropy_loss(predictions, targets, eps=1e-07)[source]
Compute binary cross-entropy loss.
- Parameters:
predictions (Array) – Model predictions (after sigmoid) [batch_size]
targets (Array) – Binary targets (0 or 1) [batch_size]
eps (float) – Small constant for numerical stability
- Returns:
Scalar loss value
- Return type:
Array
-
nabla.nn.losses.classification.softmax_cross_entropy_loss(logits, targets, axis=-1)[source]
Compute softmax cross-entropy loss (numerically stable).
This is equivalent to cross_entropy_loss but more numerically stable
by combining softmax and cross-entropy computations.
- Parameters:
logits (Array) – Raw model outputs [batch_size, num_classes]
targets (Array) – One-hot encoded targets [batch_size, num_classes]
axis (int) – Axis along which to compute softmax
- Returns:
Scalar loss value
- Return type:
Array
