memcpy(&danalytical[0], TF_TensorData(analytical_tensor),
           TF_TensorByteSize(analytical_tensor));

    for (int j = 0; j < num_elem_numerical; j++) {
      ASSERT_NEAR(dnumerical[j], danalytical[j], abs_error);
    }
    TF_DeleteTensor(analytical_tensor);
    TF_DeleteTensor(numerical_tensor);
    delete[] danalytical;
    delete[] dnumerical;
    outputs[i]->Unref();
  }
}

  float* dnumerical = new float[num_elem_numerical]{0};
  memcpy(&dnumerical[0], TF_TensorData(numerical_tensor),
         TF_TensorByteSize(numerical_tensor));

  for (int j = 0; j < num_grad; j++) {
    ASSERT_NEAR(dnumerical[j], expected_grad[j], abs_error);
  }
  delete[] dnumerical;
  TF_DeleteTensor(numerical_tensor);
}

Status MatMulModel(AbstractContext* ctx,