TaggedValue valuef(3.f);
  TaggedValue valuei(int64_t(3));
  TaggedValue list = TaggedValue::List();
  TaggedValue tuple = TaggedValue::Tuple();
  tuple.tuple().push_back(TaggedValue(int64_t(310)));
  list.list().push_back(valuei);
  list.list().push_back(valuef);
  list.list().push_back(tuple);
  std::stringstream stream;
  stream << list;
  ASSERT_EQ(stream.str(), "[3, 3, (310, ), ]");
}

TEST(ValueTest, TestString) {

  *(config_1.mutable_tf_record()->mutable_path()) = "test_path_1";
  representative_dataset_configs.push_back(config_1);

  // Signature key is implicitly "serving_default".
  RepresentativeDatasetConfig config_2{};
  *(config_2.mutable_tf_record()->mutable_path()) = "test_path_2";
  representative_dataset_configs.push_back(config_2);

  const absl::StatusOr<
      absl::flat_hash_map<std::string, RepresentativeDatasetFile>>

  auto shift = op.input(1);
  auto axis = op.input(2);
  auto grad_op = Roll(scope, grad_inputs[0], Neg(scope, shift), axis);
  grad_outputs->push_back(grad_op);
  grad_outputs->push_back(NoGradient());
  grad_outputs->push_back(NoGradient());
  return scope.status();
}
REGISTER_GRADIENT_OP("Roll", RollGrad);

}  // namespace
}  // namespace ops

  for (int i = 0; i < num_inputs; i++) {
    func_inputs.push_back(op.input(i));
    input_dtypes.push_back(op.input_type(i));
  }

  func_inputs.insert(std::end(func_inputs), std::begin(grad_inputs),
                     std::end(grad_inputs));

  auto grad = SymbolicGradient(scope, func_inputs, input_dtypes, f);
  for (int i = 0; i < num_inputs; i++) {
    grad_outputs->push_back(grad[i]);
  }

  return scope.status();
}

    output_args_.push_back(arg);
  }
  // Parse the attributes.
  for (const OpDef::AttrDef& attr_def : op_def.attr()) {
    AttrSpec attr = AttrSpec::Create(attr_def);
    // Only non-inferred args are added as arguments.
    if (inferred_attrs.find(attr_def.name()) == inferred_attrs.end()) {
      argument_attrs_.push_back(attr);
    }
  }
}

}  // namespace generator

  args.reserve(real_argc + 1);
  for (int i = 0; i < real_argc; i++) {
    args.push_back(real_argv[i]);
  }

  struct FreeDeleter {
    void operator()(char* ptr) { free(ptr); }
  };

  std::unique_ptr<char, FreeDeleter> enable_global_jit_arg(
      strdup("--tf_xla_cpu_global_jit=true"));
  args.push_back(enable_global_jit_arg.get());

  std::unique_ptr<char, FreeDeleter> reduce_min_cluster_size_arg(

        auto newTy = QuantizedType::castToExpressedType(operand.getType());
        newOperands.push_back(
            rewriter.create<TFL::DequantizeOp>(loc, newTy, operand));
        continue;
      }

      newOperands.push_back(operand);
    }

    SmallVector<Type> newResultTys;
    for (auto result : op->getResults()) {
      Type resultTy = result.getType();

  result.reserve(set.size());
  for (DataType dt : set) {
    result.push_back(dt);
  }
  return result;
}

std::vector<std::vector<int64_t>> InterestingShapes() {
  std::vector<std::vector<int64_t>> interesting_shapes;
  interesting_shapes.push_back({});             // Scalar
  interesting_shapes.push_back({10});           // 1D Vector
  interesting_shapes.push_back({3, 3});         // 2D Matrix

    if (aggregator_ops_to_ignore.count(op.getId().str())) continue;

    ids.push_back(op.getId());
    calibration_methods.push_back(op.getCalibrationMethod());
    statistics_outputs.push_back(op.getMin());
    statistics_outputs.push_back(op.getMax());
    statistics_outputs.push_back(op.getHistogram());
  }
}

// Inserts a `CalibrationStatisticsSaverOp` to the end of the region.

      .def("front", &mlir::Region::front, py::return_value_policy::reference)
      .def("add_block", [](mlir::Region& r) { r.push_back(new mlir::Block); })
      .def("push_back", &mlir::Region::push_back)
      .def("size", [](mlir::Region& r) { return r.getBlocks().size(); })
      .def("front", &mlir::Region::front, py::return_value_policy::reference);