oa::ml::nn::Rnn
Stacked batch-first Elman recurrent network using whole-sequence GPU scans. Input uses [batch, sequence, input]; output uses [batch, sequence, hidden]. Every layer starts from a zero hidden state.
Declaration
pub struct Rnn { /* private fields */ }Public Rust declaration.
Public Methods
Associated Functions
pub fn new_with_seed( input_size: usize, hidden_size: usize, num_layers: usize, seed: u64, ) -> Result<Self>pub fn new_with_seed_on( engine: &Engine, input_size: usize, hidden_size: usize, num_layers: usize, seed: u64, ) -> Result<Self>pub fn new_with_seed_and_bias( input_size: usize, hidden_size: usize, num_layers: usize, bias: bool, seed: u64, ) -> Result<Self>pub fn new_with_seed_and_bias_on( engine: &Engine, input_size: usize, hidden_size: usize, num_layers: usize, bias: bool, seed: u64, ) -> Result<Self>Public Method Documentation
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
Construct a deterministically initialized stacked RNN with biases. Errors Returns an error when a dimension or layer count is zero, hidden size exceeds the 1024-element scan limit, arithmetic overflows, or parameter allocation and registration fail.
No public source comment is attached to this declaration.
Construct a deterministically initialized stacked RNN with biases. Errors Returns an error when a dimension or layer count is zero, hidden size exceeds the 1024-element scan limit, arithmetic overflows, or parameter allocation and registration fail.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.
No public source comment is attached to this declaration.