if (op->getNumOperands() != 5) {
      op->emitError()
          << "We're expecting 5 inputs for UnidirectionalSequenceRNN, only "
          << op->getNumOperands() << " provided";
      return failure();
    }

    if (op->getNumResults() != 2) {
      op->emitError()
          << "We're expecting 2 inputs for UnidirectionalSequenceRNN, only "
          << op->getNumResults() << " found";
      return failure();
    }

    "'LastState' type: DT_FLOAT } output_arg: { name: 'Output' type: DT_FLOAT} "
    "attr : { name: '_tflite_input_indices' type: 'list(int)'}";

constexpr mlir::StringRef kUnidirectionalSequenceRnnOp =
    "name: 'UnidirectionalSequenceRnn' input_arg: {name: 'Input' type: "
    "DT_FLOAT} input_arg: { name: 'Weights' type: DT_FLOAT } "
    "input_arg: { name: 'RecurrentWeights' type: DT_FLOAT } input_arg: { "
    "name: 'Bias' type: DT_FLOAT} "

  %3 = "tf.Const"() {device = "", dtype = f32, value = dense<0.000000e+00>: tensor<1x28xf32>} : () -> tensor<1x28xf32>
  %4:2 = "tf.UnidirectionalSequenceRnn"(%arg, %1, %1, %2, %3) {_tflite_input_indices = [0, 1, 2, 3, 4], device = ""} : (tensor<28x1x28xf32>, tensor<28x28xf32>, tensor<28x28xf32>, tensor<28xf32>, tensor<1x28xf32>) -> (tensor<*xf32>, tensor<28x1x28xf32>)

      return {1,  2,  3,  4,  5,  6,  7,  8,  9,  10, 11, 16, 18, 19, 20, 21,
              22, 23, 24, 25, 26, 27, 28, 33, 40, 41, 42, 43, 44, 45, 46, 47};
    }
  }];
}

// UnidirectionalSequenceRNN op.
def TFL_UnidirectionalSequenceRNNOp : TFL_Op<"unidirectional_sequence_rnn", [
    TFL_OperandHasRank<4, 2>,
    PredOpTrait<"input and output must have same element type",