TF_TensorByteSize(theta_tensor));

  // Initialize space for the numerical gradient.
  vector<float> dtheta_approx(num_elems);

  // Get theta shape and store in theta_dims.
  int num_dims = TF_NumDims(theta_tensor);
  vector<int64_t> theta_dims(num_dims);
  GetDims(theta_tensor, theta_dims.data());

  // Initialize auxilary data structures.

// Transfers up to `size` bytes from `dst_fd` to `src_fd`.
//
// This method uses a temporary buffer to hold contents.
int CopyFileContents(int dst_fd, int src_fd, off_t size) {
  // Use a copy buffer of 128KB but don't store it on the stack.
  constexpr static size_t kPosixCopyFileBufferSize = 128 * 1024;
  std::unique_ptr<char[]> buffer(new char[kPosixCopyFileBufferSize]);

  off_t offset = 0;
  int bytes_transferred = 0;
  int rc = 1;

  if (UseFunction()) {
    // TODO(b/168850692): Enable this.
    GTEST_SKIP() << "Can't take gradient of "
                    "SparseSoftmaxCrossEntropyWithLogits in tracing mode.";
  }

  // Score
  float X_vals[] = {1.0f, 2.0f, 3.0f, -5.0f, -4.0f, -3.0f, 2.0f, 0.0f, -1.0f};
  int64_t X_dims[] = {3, 3};
  AbstractTensorHandlePtr X;
  {
    AbstractTensorHandle* X_raw;