Interpreting -> AllocateTensors() on Spresense and TFlite fails

constexprintTensorArenaSize=900000;
uint8_tensor_area [kTensorArenaSize];

void setup() {
  Serial.begin (115200);
  tflite::InitializeTarget();
  memset(tensor_area, 0, kTensorArenaSize*sizeof(uint8_t));
  
  // Setup logging. 
  static tflite::MicroErrorReporter micro_error_reporter;
  error_reporter=&micro_error_reporter;
  

// This pull in all the operations implementations needed.
  static tflite::AllOpsResolver resolver;
  
  // Build an interpreter to run the model with.
  static tflite:: MicroInterpreter static_interpreter(
      model, resolver, tensor_area, kTensorArenaSize, error_reporter);
  interpreter=&static_interpreter;
  
  // Allocate memory from the sensor_area for the model's sensors.
  TfLiteStatus allocate_status=interpreter->AllocateTensors();
  if(allocate_status!=kTfLiteOk){
    Serial.println("AllocateTensors() failed";
    return;
  } else{
    Serial.println("AllocateTensor()Success";
  }