Struct cmsis_nn_gru_gate_f16¶

Defined in File arm_nn_types_flt.h

Struct Documentation¶

struct cmsis_nn_gru_gate_f16¶

Weights and biases for a single float16 GRU gate.

The activation (sigmoid for update/reset, tanh for candidate) is implied by the gate’s role and is not stored here. The reset-after formulation keeps the input-projection bias and the recurrent-projection bias separate, because the reset gate multiplies the recurrent projection (including its bias) after the matmul.

Public Members

const float16_t *input_weights¶: Input-to-gate weight matrix [hidden_size, input_size].

const float16_t *hidden_weights¶: Hidden-to-gate weight matrix [hidden_size, hidden_size].

const float16_t *input_bias¶: Optional input-projection bias [hidden_size]. May be NULL.

const float16_t *hidden_bias¶: Optional recurrent-projection bias [hidden_size]. May be NULL.