torch.nn.modules.linear
package torch.nn.modules.linear
Members list
Grouped members
nn_linear
final class Identity[D <: DType](args: Any*)(implicit evidence$1: Default[D]) extends TensorModule[D]
A placeholder identity operator that is argument-insensitive.
A placeholder identity operator that is argument-insensitive.
Attributes
- Source
- Identity.scala
- Supertypes
final class Linear[ParamType <: FloatNN](inFeatures: Long, outFeatures: Long, addBias: Boolean)(implicit evidence$1: Default[ParamType]) extends HasParams[ParamType], HasWeight[ParamType], TensorModule[ParamType]
Applies a linear transformation to the incoming data: $y = xA^T + b$
Applies a linear transformation to the incoming data: $y = xA^T + b$
This module supports TensorFloat32<tf32_on_ampere>.
Example:
import torch.*
val linear = nn.Linear[Float32](20, 30)
val input = torch.rand(Seq(128, 20))
println(linear(input).size) // ArraySeq(128, 30)
Value parameters
- bias
-
If set to
false, the layer will not learn an additive bias. Default:true - inFeatures
-
size of each input sample
- outFeatures
-
size of each output sample
Attributes
- Source
- Linear.scala
- Supertypes
In this article