LSTM Type

Long short-term memory (LSTM) recurrent neural network.

Constructors

Constructor Description

LSTM(inputSize, hiddenSize, ?numLayers, ?bias, ?batchFirst, ?dropout, ?bidirectional)

Full Usage: LSTM(inputSize, hiddenSize, ?numLayers, ?bias, ?batchFirst, ?dropout, ?bidirectional)

Parameters:
    inputSize : int
    hiddenSize : int
    ?numLayers : int
    ?bias : bool
    ?batchFirst : bool
    ?dropout : float
    ?bidirectional : bool

Returns: LSTM
inputSize : int
hiddenSize : int
?numLayers : int
?bias : bool
?batchFirst : bool
?dropout : float
?bidirectional : bool
Returns: LSTM

Instance members

Instance member Description

this.forwardWithHidden (input, hidden, cell)

Full Usage: this.forwardWithHidden (input, hidden, cell)

Parameters:
Returns: Tensor * Tensor * Tensor
input : Tensor
hidden : Tensor
cell : Tensor
Returns: Tensor * Tensor * Tensor

this.hiddenSize

Full Usage: this.hiddenSize

Returns: int
Returns: int

this.inputSize

Full Usage: this.inputSize

Returns: int
Returns: int

this.newHidden batchSize

Full Usage: this.newHidden batchSize

Parameters:
    batchSize : int

Returns: Tensor
batchSize : int
Returns: Tensor

© Copyright 2021, DiffSharp Contributors.