// CHECK-DAG: %[[q_w:.*]] = "tf.Const"() <{value = #tf_type<tensor_proto : "0x746674
// CHECK-DAG: %[[w_scale:.*]] = "tf.Const"() <{value = dense<0.0157480314> : tensor<f32>}> : () -> tensor<f32>
// CHECK-DAG: %[[w_zp:.*]] = "tf.Const"() <{value = dense<0> : tensor<i32>}> : () -> tensor<i32>

// CHECK-DAG: {{\[\[\[}}-87, -42]

// CHECK: %[[quantize:.*]] = "tf.PartitionedCall"(%arg0, %[[in_scale]], %[[in_zp]])
// CHECK-SAME: f = @quantize_i8
// CHECK: %[[conv_quant:.*]] = "tf.PartitionedCall"(%[[quantize]], %[[w_quant]], %[[b_quant]],
// CHECK-SAME: %[[in_scale]], %[[in_zp]], %[[w_scale]], %[[w_zp]],
// CHECK-SAME: %[[b_scale]], %[[w_zp]], %[[out_scale]], %[[out_zp]])
// CHECK-SAME: f = @quantized_conv2d_with_bias_and_relu6_fn_0

    "'h_scale' type: 'float'} attr : { name: 'max_classes_per_detection' "
    "type: 'int'} attr : { name: 'max_detections' type: 'int'} attr : { "
    "name: 'nms_iou_threshold' type: 'float'} attr : { name: "
    "'nms_score_threshold' type: 'float'} attr : { name: 'num_classes' type: "
    "'int'} attr : { name: 'w_scale' type: 'float'} attr : { name: 'x_scale' "

// CHECK-DAG: %[[w0_quantized:.*]] = "tf.Const"() <{value = dense<{{\[\[\[\[}}-42, 18
// CHECK-DAG: %[[in_scale:.*]] = "tf.Const"() <{value = dense<0.0039215642> : tensor<f32>}> : () -> tensor<f32>
// CHECK-DAG: %[[in_out_zp:.*]] = "tf.Const"() <{value = dense<-128> : tensor<i32>}> : () -> tensor<i32>
// CHECK-DAG: %[[w0_scale:.*]] = "tf.Const"() <{value = dense<0.0150353173> : tensor<f32>}> : () -> tensor<f32>

	Status                           *v1beta2.ScaleStatus `json:"status,omitempty"`
}

// ScaleApplyConfiguration constructs an declarative configuration of the Scale type for use with
// apply.
func Scale() *ScaleApplyConfiguration {
	b := &ScaleApplyConfiguration{}
	b.WithKind("Scale")
	b.WithAPIVersion("apps/v1beta2")
	return b
}

// WithKind sets the Kind field in the declarative configuration to the given value

}

// ScaleApplyConfiguration constructs an declarative configuration of the Scale type for use with
// apply.
func Scale() *ScaleApplyConfiguration {
	b := &ScaleApplyConfiguration{}
	b.WithKind("Scale")
	b.WithAPIVersion("autoscaling/v1")
	return b
}

// WithKind sets the Kind field in the declarative configuration to the given value

type PCIter struct {
	p       []byte
	PC      uint32
	NextPC  uint32
	PCScale uint32
	Value   int32
	start   bool
	Done    bool
}

// NewPCIter creates a PCIter with a scale factor for the PC step size.
func NewPCIter(pcScale uint32) *PCIter {
	it := new(PCIter)
	it.PCScale = pcScale
	return it
}

// Next advances it to the Next pc.
func (it *PCIter) Next() {

    for (RequantizeState& rescale : rescales) {
      if (rescale.params == quantized_type) {
        rescale.users.emplace_back(op, operand_index);
        return true;
      }
    }
    RequantizeState& rescale = rescales.emplace_back();
    rescale.pos = RequantizeState::ON_OUTPUT;
    rescale.params = quantized_type;
    rescale.users.emplace_back(op, operand_index);
    return true;
  }

	}
	return q.i.Sign()
}

// AsScale returns the current value, rounded up to the provided scale, and returns
// false if the scale resulted in a loss of precision.
func (q *Quantity) AsScale(scale Scale) (CanonicalValue, bool) {
	if q.d.Dec != nil {
		return q.d.AsScale(scale)
	}
	return q.i.AsScale(scale)
}

// RoundUp updates the quantity to the provided scale, ensuring that the value is at

  // TFR_ConstantTensorOp (
  //   ConstantOp (ConstAttr<F32Attr (in_scale[0] * in_scale[1] /
  //   out_scale))
  // )
  // Currently, all decompositions using this pattern (Conv2D, FC) have the
  // following preconditions:
  // * out_scale: float scalar attribute
  // * in_scale[0] (input scale): float scalar, given by tf.Const -> tfr.cast
  // * in_scale[1] (filter scale): float scalar/vector