[][src]Module tch::nn

Re-exports

pub use optimizer::Optimizer;

Modules

optimizer

Structs

BatchNorm2D

A batch-normalization layer.

Conv2D

A two dimension convolution layer.

Conv2DConfig
Func

A layer defined by a simple closure.

FuncT

A layer defined by a closure with an additional training parameter.

LSTM

A Long Short-Term Memory (LSTM) neural network.

Linear

A linear fully-connected layer.

Path
Sequential
SequentialT
VarStore

A VarStore is used to store variables used by one or multiple layers. It specifies a single device where all variables are stored.

Traits

Module

The simplest module trait, defining a forward function.

ModuleT

Module trait with an additional train parameter.