Documentation
¶
Overview ¶
Package training provides core components for neural network training.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Model ¶
type Model[T tensor.Numeric] interface { // Forward performs the forward pass of the model. Forward(ctx context.Context, inputs ...*tensor.TensorNumeric[T]) (*tensor.TensorNumeric[T], error) // Backward performs the backward pass of the model. Backward(ctx context.Context, grad *tensor.TensorNumeric[T], inputs ...*tensor.TensorNumeric[T]) ([]*tensor.TensorNumeric[T], error) // Parameters returns the parameters of the model. Parameters() []*graph.Parameter[T] }
Model defines the interface for a trainable model.
Directories
¶
| Path | Synopsis |
|---|---|
|
Package loss provides various loss functions for neural networks.
|
Package loss provides various loss functions for neural networks. |
|
Package optimizer provides various optimization algorithms for neural networks.
|
Package optimizer provides various optimization algorithms for neural networks. |
Click to show internal directories.
Click to hide internal directories.