Linear class - linear library

Constructors

Linear(int inFeatures, int outFeatures, {bool bias = true, Device device = Device.CPU, int seed = 0}): Weight init: Kaiming-uniform with a = sqrt(5) (matches PyTorch's default). Bias, when present, uses uniform in [-1/sqrt(fan_in), +1/sqrt(fan_in)].

bias → Tensor?: final
hashCode → int: The hash code for this object.
no setterinherited
inFeatures → int: final
outFeatures → int: final
runtimeType → Type: A representation of the runtime type of the object.
no setterinherited
training ↔ bool: Whether this module is in training mode. Layers that behave differently between training and inference (e.g. Dropout) read this flag in their call method. Defaults to training mode.
getter/setter pairinherited
weight → Tensor: final

call(Tensor x) → Tensor: Forward: x @ W.T + b. x shape [..., inFeatures], returns [..., outFeatures]. Rank-3 or higher input is handled by reshaping the leading dims into a single row axis and back.
eval() → void: Put this module (and any registered submodules) into evaluation mode.
inherited
noSuchMethod(Invocation invocation) → dynamic: Invoked when a nonexistent method or property is accessed.
inherited
parameters() → List<Tensor>: Trainable tensors owned by this module (and its submodules).
override
submodules() → List<Module>: Submodules owned by this module. Subclasses that compose other modules should override this so train() / eval() propagate. Default: empty.
inherited
toString() → String: A string representation of this object.
inherited
train() → void: Put this module (and any registered submodules) into training mode.
inherited
zeroGrad() → void: Zero every parameter's gradient. Safe to call before each backward.
inherited