[−][src]Trait opencv::dnn::prelude::RNNLayer

pub trait RNNLayer: LayerTrait {
    pub fn as_raw_RNNLayer(&self) -> *const c_void;

    pub fn as_raw_mut_RNNLayer(&mut self) -> *mut c_void;

    pub fn set_weights(
        &mut self, 
        wxh: &Mat, 
        bh: &Mat, 
        whh: &Mat, 
        who: &Mat, 
        bo: &Mat
    ) -> Result<()> { ... }

    pub fn set_produce_hidden_output(&mut self, produce: bool) -> Result<()> { ... }
}

Classical recurrent layer

Accepts two inputs @f$x_t@f$ and @f$h_{t-1}@f$ and compute two outputs @f$o_t@f$ and @f$h_t@f$.

  • input: should contain packed input @f$x_t@f$.
  • output: should contain output @f$o_t@f$ (and @f$h_t@f$ if setProduceHiddenOutput() is set to true).

input[0] should have shape [T, N, data_dims] where T and N is number of timestamps and number of independent samples of @f$x_t@f$ respectively.

output[0] will have shape [T, N, @f$N_o@f$], where @f$N_o@f$ is number of rows in @f$ W_{xo} @f$ matrix.

If setProduceHiddenOutput() is set to true then @p output[1] will contain a Mat with shape [T, N, @f$N_h@f$], where @f$N_h@f$ is number of rows in @f$ W_{hh} @f$ matrix.

Required methods

pub fn as_raw_RNNLayer(&self) -> *const c_void[src]

pub fn as_raw_mut_RNNLayer(&mut self) -> *mut c_void[src]

Loading content...

Provided methods

pub fn set_weights(
    &mut self,
    wxh: &Mat,
    bh: &Mat,
    whh: &Mat,
    who: &Mat,
    bo: &Mat
) -> Result<()>[src]

Setups learned weights.

Recurrent-layer behavior on each step is defined by current input @f$ x_t @f$, previous state @f$ h_t @f$ and learned weights as follows: @f{eqnarray*}{ h_t &= tanh&(W_{hh} h_{t-1} + W_{xh} x_t + b_h), \ o_t &= tanh&(W_{ho} h_t + b_o), @f}

Parameters

  • Wxh: is @f$ W_{xh} @f$ matrix
  • bh: is @f$ b_{h} @f$ vector
  • Whh: is @f$ W_{hh} @f$ matrix
  • Who: is @f$ W_{xo} @f$ matrix
  • bo: is @f$ b_{o} @f$ vector

pub fn set_produce_hidden_output(&mut self, produce: bool) -> Result<()>[src]

If this flag is set to true then layer will produce @f$ h_t @f$ as second output. @details Shape of the second output is the same as first output.

C++ default parameters

  • produce: false
Loading content...

Implementations

impl<'_> dyn RNNLayer + '_[src]

pub fn create(params: &LayerParams) -> Result<Ptr<dyn RNNLayer>>[src]

Creates instance of RNNLayer

Implementors

impl RNNLayer for PtrOfRNNLayer[src]

Loading content...