LSTMCell (DiffSharp)

LSTMCell Type

Namespace: DiffSharp.Model
Assembly: DiffSharp.Core.dll
Base Type: Model

Unit cell of a long short-term memory (LSTM) recurrent neural network. Prefer using the RNN class instead, which can combine RNNCells in multiple layers.

Constructors

Constructor Description

Constructor	Description
`LSTMCell(inputSize, hiddenSize, ?bias, ?checkShapes)` Full Usage: `LSTMCell(inputSize, hiddenSize, ?bias, ?checkShapes)` Parameters: inputSize : `int` hiddenSize : `int` ?bias : `bool` ?checkShapes : `bool` Returns: `LSTMCell`	inputSize : `int` hiddenSize : `int` ?bias : `bool` ?checkShapes : `bool` Returns: `LSTMCell`


                
                  
                    
                      LSTMCell(inputSize, hiddenSize, ?bias, ?checkShapes)

Full Usage: LSTMCell(inputSize, hiddenSize, ?bias, ?checkShapes)

Parameters:

inputSize : int

hiddenSize : int

?bias : bool

?checkShapes : bool

Returns: LSTMCell

inputSize : int
hiddenSize : int
?bias : bool
?checkShapes : bool

Returns: LSTMCell

Instance members

Instance member	Description
`this.forwardSequence input` Full Usage: `this.forwardSequence input` Parameters: input : `Tensor` Returns: `Tensor * Tensor`	input : `Tensor` Returns: `Tensor * Tensor`
`this.forwardSequenceWithHidden (input, hidden, cell)` Full Usage: `this.forwardSequenceWithHidden (input, hidden, cell)` Parameters: input : `Tensor` hidden : `Tensor` cell : `Tensor` Returns: `Tensor * Tensor`	input : `Tensor` hidden : `Tensor` cell : `Tensor` Returns: `Tensor * Tensor`
`this.forwardWithHidden (input, hidden, cell)` Full Usage: `this.forwardWithHidden (input, hidden, cell)` Parameters: input : `Tensor` hidden : `Tensor` cell : `Tensor` Returns: `Tensor * Tensor`	input : `Tensor` hidden : `Tensor` cell : `Tensor` Returns: `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`