res_types, res_attrs)))
      return failure();

    // Update the function type which has excluded the control args.
    func->setAttr("function_type", TypeAttr::get(rewriter.getFunctionType(
                                       arg_types, res_types)));

    // Update arg/result attributes.
    func.setAllArgAttrs(arg_attrs);
    func.setAllResultAttrs(res_attrs);

        auto min_max = GetMinMaxValuesForArgument(func_name, i);
        // The input min/max or mean/std are not specified, then skip.
        if (!min_max.first.has_value() || !min_max.second.has_value()) return;

        TypeAttr params = quant::GetQuantizedTypeAttr(
            builder, input_type, builder.getF64FloatAttr(min_max.first.value()),
            builder.getF64FloatAttr(min_max.second.value()),

        auto min_max = GetMinMaxValuesForArgument(func_name, i);
        // The input min/max or mean/std are not specified, then skip.
        if (!min_max.first.has_value() || !min_max.second.has_value()) return;

        TypeAttr params = quant::GetQuantizedTypeAttr(
            builder, input_type, builder.getF64FloatAttr(min_max.first.value()),
            builder.getF64FloatAttr(min_max.second.value()),

      return false;
    }
  }
  return true;
}

// Returns the tensor type created from the `shape_attr` and `type_attr`
// attributes.
Type GetType(Attribute shape_attr, Attribute type_attr) {
  auto shape = mlir::cast<tf_type::ShapeAttr>(shape_attr);
  auto type = mlir::cast<TypeAttr>(type_attr);
  if (shape.hasRank())
    return tensorflow::GetTypeFromTFTensorShape(shape.getShape(),

                                   mean_op.getAxis(), mean_op.getKeepDims());

  // Insert a requant op.
  rewriter.replaceOpWithNewOp<TFL::QuantizeOp>(
      mean_op, output_type, new_mean_op, mlir::TypeAttr::get(output_type));
  return success();
}

}  // namespace tac
}  // namespace TFL

  int64_t out = 0;
  for (int64_t outer = 0; outer < outer_size; ++outer) {
    for (auto op : operands) {
      auto typed_attr = op.cast<TypedAttr>();
      const int64_t dim_size =
          typed_attr.getType().cast<RankedTensorType>().getDimSize(axis);
      const int64_t inner_size = dim_size * base_inner_size;

    // types. But we need to wrap it up with ElementsAttr to construct
    // valid TensorFlow constants.
    auto typed_attr = mlir::cast<TypedAttr>(value);
    type = tensorflow::GetTypeFromTFTensorShape(/*shape=*/{},
                                                typed_attr.getType());
    return ConstOp::build(builder, result, DenseElementsAttr::get(type, value));
  }

  return builder.getI32IntegerAttr(value);
}

static mlir::Attribute BuildTypeAttr(tflite::TensorType value,
                                     mlir::Builder builder) {
  return mlir::TypeAttr::get(ConvertElementType(value, builder));
}

static mlir::Attribute BuildTFL_AFAttr(tflite::ActivationFunctionType value,
                                       mlir::Builder builder) {

    type_attr = attr_value_pb2.AttrValue(type=types_pb2.DT_QINT8)
    if quantize:
      self.assertTrue(
          self._contains_op(output_graphdef, 'Const', 'dtype', type_attr)
      )
    else:
      self.assertFalse(
          self._contains_op(output_graphdef, 'Const', 'dtype', type_attr)
      )

  @parameterized.named_parameters(

          name: "condition"
          type: DT_BOOL
        }
        input_arg {
          name: "t"
          type_attr: "T"
        }
        input_arg {
          name: "e"
          type_attr: "T"
        }
        output_arg {
          name: "output"
          type_attr: "T"
        }
        attr {
          name: "T"
          type: "type"
        }
      }
      op {