CMSIS-NN  
CMSIS NN Software Library
 
Loading...
Searching...
No Matches
LSTM Layer Functions

Functions

arm_cmsis_nn_status arm_lstm_unidirectional_s16 (const int16_t *input, int16_t *output, const cmsis_nn_lstm_params *params, cmsis_nn_lstm_context *buffers)
 LSTM unidirectional function with 16 bit input and output and 16 bit gate output, 64 bit bias.
 
arm_cmsis_nn_status arm_lstm_unidirectional_s8 (const int8_t *input, int8_t *output, const cmsis_nn_lstm_params *params, cmsis_nn_lstm_context *buffers)
 LSTM unidirectional function with 8 bit input and output and 16 bit gate output, 32 bit bias.
 

Description

Function Documentation

◆ arm_lstm_unidirectional_s16()

arm_cmsis_nn_status arm_lstm_unidirectional_s16 ( const int16_t *  input,
int16_t *  output,
const cmsis_nn_lstm_params params,
cmsis_nn_lstm_context buffers 
)

LSTM unidirectional function with 16 bit input and output and 16 bit gate output, 64 bit bias.

Parameters
[in]inputPointer to input data
[out]outputPointer to output data
[in]paramsStruct containing all information about the lstm operator, see arm_nn_types.
[in]buffersStruct containing pointers to all temporary scratch buffers needed for the lstm operator, see arm_nn_types.
Returns
The function returns ARM_CMSIS_NN_SUCCESS
  1. Supported framework: TensorFlow Lite Micro

◆ arm_lstm_unidirectional_s8()

arm_cmsis_nn_status arm_lstm_unidirectional_s8 ( const int8_t *  input,
int8_t *  output,
const cmsis_nn_lstm_params params,
cmsis_nn_lstm_context buffers 
)

LSTM unidirectional function with 8 bit input and output and 16 bit gate output, 32 bit bias.

Parameters
[in]inputPointer to input data
[out]outputPointer to output data
[in]paramsStruct containing all information about the lstm operator, see arm_nn_types.
[in]buffersStruct containing pointers to all temporary scratch buffers needed for the lstm operator, see arm_nn_types.
Returns
The function returns ARM_CMSIS_NN_SUCCESS
  1. Supported framework: TensorFlow Lite Micro