@OscarDPan, Pablo Moyano, Przemyslaw Tredak, @qitaishui, @Quarazy, @raix852,
Philipp Helo, Sam Abrahams, @SriramRamesh, Till Hoffmann, Tushar Soni, @tvn,
@tyfkda, Uwe Schmidt, Victor Villas, Vit Stepanovs, Vladislav Gubarev,
@wujingyue, Xuesong Yang, Yi Liu, Yilei Yang, @youyou3, Yuan (Terry) Tang,
Yuming Wang, Zafar Takhirov, @zhongyuk, Ziming Dong, @guotong1988

using namespace std;

// ================== Helper functions =================

// Fills data with values [start,end) with given step size.
void Range(vector<int32_t>* data, int32_t start, int32_t end,
           int32_t step = 1) {
  for (int32_t i = start; i < end; i += step) {
    (*data)[i] = i;
  }
}

// Fills out_dims with the dimensions of the given tensor.
void GetDims(const TF_Tensor* t, int64_t* out_dims) {

// * TF_Status holds error information.  It is an object type
//   and therefore is passed around as a pointer to an opaque
//   struct as mentioned above.
// * Every call that has a TF_Status* argument clears it on success
//   and fills it with error info on failure.
// * unsigned char is used for booleans (instead of the 'bool' type).
//   In C++ bool is a keyword while in C99 bool is a macro defined
//   in stdbool.h. It is possible for the two to be inconsistent.

  void PopState() { call_state_.pop(); }

 private:
  // Helper for Accumulate: uses a GradientTape to compute forward gradients
  // from a backward gradient function. Fills `out_grads` corresponding to
  // `output_tensors`. `out_grads` must not be null.
  //
  // Executes the backward function in order to trace its gradient, which will