How do I optimize memory usage for a neural network running on an ARM Cortex-M4 using CMSIS-NN?

#include "arm_nnfunctions.h"

void run_nn(const q7_t* input_data) {
  q7_t intermediate_buffer[INTERMEDIATE_SIZE];
  q7_t output_data[OUTPUT_SIZE];
  // Run the network layers
  arm_convolve_HWC_q7_basic(input_data, CONV1_WEIGHT, CONV1_BIAS, intermediate_buffer

#include "arm_nnfunctions.h"

void run_nn(const q7_t* input_data) {
  q7_t intermediate_buffer[INTERMEDIATE_SIZE];
  q7_t output_data[OUTPUT_SIZE];
  // Run the network layers
  arm_convolve_HWC_q7_basic(input_data, CONV1_WEIGHT, CONV1_BIAS, intermediate_buffer