Struct SimpleRecurrentLayerParams 

pub struct SimpleRecurrentLayerParams {
    pub input_vector_size: u64,
    pub output_vector_size: u64,
    pub activation: Option<ActivationParams>,
    pub sequence_output: bool,
    pub has_bias_vector: bool,
    pub weight_matrix: Option<WeightParams>,
    pub recursion_matrix: Option<WeightParams>,
    pub bias_vector: Option<WeightParams>,
    pub reverse_input: bool,
}

A simple recurrent layer.

.. code::

  y_t = SimpleRecurrentLayer(x_t, y_{t-1})

Input A blob of rank 5, with shape `[Seq, Batch, inputVectorSize, 1, 1]. This represents a sequence of vectors of size inputVectorSize. Output Same rank as the input. Represents a vector of size outputVectorSize``. It is either the final output or a sequence of outputs at all time steps.

• Output Shape: \[1, Batch, outputVectorSize, 1, 1\] , if sequenceOutput == false
• Output Shape: \[Seq, Batch, outputVectorSize, 1, 1\] , if sequenceOutput == true

This layer is described by the following equation:

.. math:: \boldsymbol{y_t} = f(\mathrm{clip}(W \boldsymbol{x_t} +
R \boldsymbol{y_{t-1}} + b))

• W is a 2-dimensional weight matrix (\[outputVectorSize, inputVectorSize\], row-major)
• R is a 2-dimensional recursion matrix (\[outputVectorSize, outputVectorSize\], row-major)
• b is a 1-dimensional bias vector (\[outputVectorSize\])
• f() is an activation
• clip() is a function that constrains values between \[-50.0, 50.0\]

Fields

input_vector_size: u64

The size of the input vectors.

output_vector_size: u64

The size of the output vectors.

activation: Option<ActivationParams>

Activations supported are Linear, Sigmoid, Tanh, ReLU, Scaled Tanh (alpha = 1.71, beta = 2/3), Hard sigmoid (alpha = 0.2, beta = 0.5)

The activation function.

sequence_output: bool

If false output is just the result after final state update. If true, output is a sequence, containing outputs at all time steps.

has_bias_vector: bool

If false, no bias is added.

weight_matrix: Option<WeightParams>

Weight matrix W.

recursion_matrix: Option<WeightParams>

Recursion Weight matrix R.

bias_vector: Option<WeightParams>

Bias vector b.

reverse_input: bool

If true, then the node processes the input sequence from right to left

Trait Implementations

impl Clone for SimpleRecurrentLayerParams

fn clone(&self) -> SimpleRecurrentLayerParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SimpleRecurrentLayerParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for SimpleRecurrentLayerParams

fn default() -> Self

Returns the “default value” for a type.

impl Message for SimpleRecurrentLayerParams

fn encoded_len(&self) -> usize

Returns the encoded length of the message without a length delimiter.

fn clear(&mut self)

Clears the message, resetting all fields to their default.

fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message to a buffer.

fn encode_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message to a newly allocated buffer.

fn encode_length_delimited( &self, buf: &mut impl BufMut, ) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message with a length-delimiter to a buffer.

fn encode_length_delimited_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message with a length-delimiter to a newly allocated buffer.

fn decode(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes an instance of the message from a buffer.

fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes a length-delimited instance of the message from the buffer.

fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes an instance of the message from a buffer, and merges it into self.

fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes a length-delimited instance of the message from buffer, and merges it into self.

impl PartialEq for SimpleRecurrentLayerParams

fn eq(&self, other: &SimpleRecurrentLayerParams) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for SimpleRecurrentLayerParams