RNN#

Overview#

A primitive to compute recurrent neural network layers. More…

// enums

enum dnnl::rnn_direction;
enum dnnl::rnn_flags;

// structs

struct dnnl::augru_backward;
struct dnnl::augru_forward;
struct dnnl::gru_backward;
struct dnnl::gru_forward;
struct dnnl::lbr_augru_backward;
struct dnnl::lbr_augru_forward;
struct dnnl::lbr_gru_backward;
struct dnnl::lbr_gru_forward;
struct dnnl::lstm_backward;
struct dnnl::lstm_forward;
struct dnnl::rnn_primitive_desc_base;
struct dnnl::vanilla_rnn_backward;
struct dnnl::vanilla_rnn_forward;

// global functions

dnnl_rnn_flags_t dnnl::convert_to_c(rnn_flags flags);
dnnl_rnn_direction_t dnnl::convert_to_c(rnn_direction dir);

Detailed Documentation#

A primitive to compute recurrent neural network layers.

Global Functions#

dnnl_rnn_flags_t dnnl::convert_to_c(rnn_flags flags)

Converts RNN cell flags enum value from C++ API to C API type.

Parameters:

flags

C++ API RNN cell flags enum value.

Returns:

Corresponding C API RNN cell flags enum value.

dnnl_rnn_direction_t dnnl::convert_to_c(rnn_direction dir)

Converts RNN direction enum value from C++ API to C API type.