// HISTOGRAM-MSE-BRUTEFORCE-CHECK-NEXT:  "tf.AddV2"
// HISTOGRAM-MSE-BRUTEFORCE-CHECK-NEXT:  return

// HISTOGRAM-MSE-BRUTEFORCE-CHECK: func @composite_conv2d_with_relu6_fn
// HISTOGRAM-MSE-BRUTEFORCE-CHECK-NEXT:  "tf.Conv2D"
// HISTOGRAM-MSE-BRUTEFORCE-CHECK-NEXT:  "tf.Relu6"
// HISTOGRAM-MSE-BRUTEFORCE-CHECK-NEXT:  return

// CalibrationOptions(

		runSubTestUserArenaNew(t, sp, true)

		spm := &smallPointerMix{sp, 5, nil, [11]byte{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11}}
		runSubTestUserArenaNew(t, spm, true)

		mse := new(mediumScalarEven)
		for i := range mse {
			mse[i] = 121
		}
		runSubTestUserArenaNew(t, mse, true)

		mso := new(mediumScalarOdd)
		for i := range mso {
			mso[i] = 122
		}
		runSubTestUserArenaNew(t, mso, true)

		mpe := new(mediumPointerEven)

      return x + 1

  model = AddOneModel()

  x_train = tf.constant([1, 2, 3, 4, 5], dtype=tf.float32)
  y_train = tf.constant([2, 3, 4, 5, 6], dtype=tf.float32)

  model.compile(optimizer='sgd', loss='mse')
  model.fit(x_train, y_train, epochs=1)

  path = tempdir + '/add_one_model'
  model.save(path)
  return path


class TensorflowToStableHLOTest(test.TestCase):

  def test_saved_model_to_stablehlo(self):

    // Use the histogram mid values that minimize MSE error.
    // This is very slow algorithm because it computes all errors for all
    // histogram mid value pairs. Therefore the value of num_bins is recommended
    // to be 256 or less.
    CALIBRATION_METHOD_HISTOGRAM_MSE_BRUTEFORCE = 4;
    // Use the histogram mid values that minimize MSE error.

  def _get_min_max_value_by_expanding_range(
      self, start_idx: int
  ) -> tuple[float, float]:
    """Starting from start_idx, expand left and right alternately to find the min value of mse loss.

    Args:
      start_idx: Index to start quantization.

    Returns:
      (min_value, max_value): Min and max calculated.
    """
    # Tuple of (mse_error, quant_min, quant_max).

    *   Update metric name to always reflect what the user has given in compile.
        Affects following cases
    *   When name is given as 'accuracy'/'crossentropy'
    *   When an aliased function name is used eg. 'mse'
    *   Removing the `weighted` prefix from weighted metric names.
    *   Allow non-Tensors through v2 losses.
    *   Add v2 sparse categorical crossentropy metric.