Error when load tflite model with c++

I transform a machine translation model to tflite format. And I can successfully load it in Java for android.
But I need to build it to a library for for other applications to call. So I try to load this model from c++ API.
I followed the example here Compila TensorFlow Lite con CMake to build the libtensorflow-lite.a. Then I try to load tflite model like this:

#include <cstdio>
#include "tensorflow/lite/interpreter.h"
#include "tensorflow/lite/kernels/register.h"
#include "tensorflow/lite/model.h"
#include "tensorflow/lite/optional_debug_tools.h"

// This is an example that is minimal to read a model
// from disk and perform inference. There is no data being loaded
// that is up to you to add as a user.
// NOTE: Do not add any dependencies to this that cannot be built with
// the minimal makefile. This example must remain trivial to build with
// the minimal build tool.
// Usage: minimal <tflite model>

#define TFLITE_MINIMAL_CHECK(x)                              \
  if (!(x)) {                                                \
    fprintf(stderr, "Error at %s:%d\n", __FILE__, __LINE__); \
    exit(1);                                                 \

int main(int argc, char* argv[]) {
  if (argc != 2) {
    fprintf(stderr, "minimal <tflite model>\n");
    return 1;
  const char* filename = argv[1];

  // Load model
  std::unique_ptr<tflite::FlatBufferModel> model =
  TFLITE_MINIMAL_CHECK(model != nullptr);

  // Build the interpreter with the InterpreterBuilder.
  // Note: all Interpreters should be built with the InterpreterBuilder,
  // which allocates memory for the Interpreter and does various set up
  // tasks so that the Interpreter can read the provided model.
  tflite::ops::builtin::BuiltinOpResolver resolver;
  tflite::InterpreterBuilder builder(*model, resolver);
  std::unique_ptr<tflite::Interpreter> interpreter;
  TFLITE_MINIMAL_CHECK(interpreter != nullptr);

  // Allocate tensor buffers.
  TFLITE_MINIMAL_CHECK(interpreter->AllocateTensors() == kTfLiteOk);
  printf("=== Pre-invoke Interpreter State ===\n");

  // Fill input buffers
  // TODO(user): Insert code to fill input tensors.
  // Note: The buffer of the input tensor with index `i` of type T can
  // be accessed with `T* input = interpreter->typed_input_tensor<T>(i);`
  int* input = interpreter->typed_input_tensor<int>(0);
  *input = 3800;

  // Run inference
  TFLITE_MINIMAL_CHECK(interpreter->Invoke() == kTfLiteOk);
  printf("\n\n=== Post-invoke Interpreter State ===\n");

  // Read output buffers
  // TODO(user): Insert getting data out code.
  // Note: The buffer of the output tensor with index `i` of type T can
  // be accessed with `T* output = interpreter->typed_output_tensor<T>(i);`

  return 0;

And it return an error said:

ERROR: Select TensorFlow op(s), included in the given model, is(are) not supported by this interpreter. Make sure you apply/link the Flex delegate before inference. For the Android, it can be resolved by adding "org.tensorflow:tensorflow-lite-select-tf-ops" dependency. See instructions:
ERROR: Node number 962 (FlexTensorListReserve) failed to prepare.

Is there any tips for this? Any advice is appreciate. Thx!

To include select ops in lite-run time build through cmake, you need to build the select ops run time using bazel and declare the dependency in target_link_libraries as mentioned in this thread. Thank you!