mxnet-nn-0.0.1.3: Train a neural network with MXNet in Haskell.

Safe HaskellNone
LanguageHaskell2010

MXNet.NN.Types

Synopsis

Documentation

data Parameter a Source #

A parameter is two NDArray to back a Symbol

Constructors

Parameter 

Instances

(Pretty a, DType a) => Show (Parameter a) Source # 

data Session a Source #

Session is all the Parameters and a Context type Session a = (M.HashMap String (Parameter a), Context)

Constructors

Session 

type TrainM a m = StateT (Session a) m Source #

TrainM is a StateT monad

type Initializer a = Context -> [Int] -> IO (NDArray a) Source #

Initializer is about how to create a NDArray from a given shape.

Usually, it can be a wrapper of MXNet operators, such as random_uniform, random_normal, random_gamma, etc..