GLUOp class
Gated Linear Unit (GLU) activation function.
Equivalent to F.glu() in PyTorch.
Formula
GLU(a, b) = a * sigmoid(b)
where [a, b] = split(input, dim).
The specified dimension must have even size, and the output halves that dimension.
final result = GLUOp(dim: -1)(tensor);
- Inheritance
-
- Object
- TransformOp
- GLUOp
- Mixed-in types
Properties
- capabilities → OperationCapabilities
-
The capabilities of this operation.
no setteroverride
- dim → int
-
The dimension along which to split. Supports negative indexing.
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- name → String
-
The human-readable name of this operation.
no setteroverride
- requiresContiguous → bool
-
Whether this operation requires contiguous input.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
apply(
TensorBuffer input) → TensorBuffer -
Applies this transform to
inputand returns the result.override -
call(
TensorBuffer input) → TensorBuffer -
Alias for apply.
inherited
-
cloneForModification(
TensorBuffer input) → TensorBuffer -
Creates an output buffer from input, ensuring contiguity with single copy.
inherited
-
computeOutputShape(
List< int> inputShape) → List<int> -
Computes the output shape for a given
inputShape.override -
ensureContiguous(
TensorBuffer input) → TensorBuffer -
Returns a contiguous version of
inputif needed.inherited -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited