Enum coaster_nn::RnnNetworkMode

pub enum RnnNetworkMode {
    ReLU,
    Tanh,
    LSTM,
    GRU,
}

Network Type for RNN Networks [cudnnRNNMOde_t][1] [1]: https://docs.nvidia.com/deeplearning/sdk/cudnn-api/index.html#cudnnRNNMode_t

Variants

ReLU

CUDNN_RNN_RELU - Single gate RNN with a ReLU activation function

Tanh

Single-gate RNN with a tanh activation function

LSTM

Four-gate LSTM Network with no peephole connection

GRU

Three-gate network with Gated Recurrent Units

Implementations

impl RnnNetworkMode

pub fn from_string(input: &str) -> Result<Self, &str>

Convert RnnNetworkMode to String Representation

Trait Implementations

impl Clone for RnnNetworkMode

fn clone(&self) -> RnnNetworkMode

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for RnnNetworkMode

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

Formats the value using the given formatter.

impl Display for RnnNetworkMode

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

Formats the value using the given formatter.

impl PartialEq for RnnNetworkMode

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

This method tests for self and other values to be equal, and is used by ==.

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

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

impl Copy for RnnNetworkMode

impl Eq for RnnNetworkMode

impl StructuralPartialEq for RnnNetworkMode