RunOptions run_options;

    Tensor input_a = CreateInputTensor(shape, 0);
    Tensor input_b = CreateInputTensor(shape, shape.num_elements());
    Tensor input_c = CreateInputTensor(shape, 2 * shape.num_elements());
    TF_RETURN_IF_ERROR(session->Run(
        run_options,
        {std::make_pair("a", input_a), std::make_pair("b", input_b),
         std::make_pair("c", input_c)},
        {"m"}, {}, &golden_output_tensors, nullptr));

        readingList.add(toKatakana(text));
        return readingList;
    }

    protected String toKatakana(final String inputStr) throws IOException {
        final StringBuilder kanaBuf = new StringBuilder();

        final Reader rd = new StringReader(inputStr);
        try (TokenStream stream = createTokenStream(rd)) {
            if (stream == null) {
                throw new IOException("Invalid tokenizer.");

// CHECK-DAG: %[[input_18:.*]] = "quantfork.stats"({{.*}}) <{layerStats = dense<[-8.000000e-01, 1.600000e+00]> : tensor<2xf32>}> : (tensor<1x4xf32>) -> tensor<1x4xf32>
// CHECK-DAG: %[[input_19:.*]] = "quantfork.stats"({{.*}}) <{layerStats = dense<[-2.000000e+00, 4.000000e+00]> : tensor<2xf32>}> : (tensor<1x2xf32>) -> tensor<1x2xf32>

@__forward_call_369(%arg0: tensor<16x224x224x3xf32> {tf._user_specified_name = "inputs"}, %arg1: tensor<*x!tf_type.resource>, %arg2: tensor<*x!tf_type.resource>, %arg3: tensor<*x!tf_type.resource>, %arg4: tensor<*x!tf_type.resource>) -> (tensor<?x?xf32>, tensor<*xf32>, tensor<?x16384xf32>, tensor<16x112x112x?xf32>, tensor<16x224x224x3xf32>, tensor<*xf32>) attributes {tf.entry_function = {control_outputs = "", inputs = "inputs_0,conv1_conv2d_readvariableop_resource,conv1_biasadd_readvariableop_resource...

    tf_device.return %input0, %arg2 : tensor<*xf32>, tensor<*xi32>
  }
  func.return

// CHECK:      tf_device.replicate
// CHECK-SAME: ([%[[ARG_0]], %[[ARG_1]]] as %[[INPUT_0:[a-z0-9]*]]: tensor<*xf32>)
// CHECK-SAME: n = 2
// CHECK-NEXT:   tf_device.return %[[INPUT_0]], %[[ARG_2]]
}

// -----

// CHECK-LABEL: func @replicate_with_devices
func.func @replicate_with_devices() {

module {
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> attributes {tf.entry_function = {inputs = "input0,input1,input2,input3", outputs = "output"}} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

// RUN: tf-opt -split-input-file -verify-diagnostics -tf-tpu-annotate-dynamic-shape-inputs %s | FileCheck %s

// Test that annotate the inputs of the cluster func to be dynamic shaped.

module attributes {tf.devices = ["/job:worker/replica:0/task:0/device:CPU:0", "/job:worker/replica:0/task:0/device:TPU_SYSTEM:0", "/job:worker/replica:0/task:0/device:TPU:0"]} {
   func.func @main(
      %arg0: tensor<2048xi64> {tf.device = "/job:localhost/replica:0/task:0/device:CPU:0"},

        private final ModelType<T> type;
        private final List<ModelReference<?>> inputs;

        private UnmanagedElementCreationAction(ModelRuleDescriptor descriptor, ModelReference<?> subject, List<ModelReference<?>> inputs, ModelType<T> type) {
            this.subject = subject;
            this.inputs = inputs;
            this.descriptor = descriptor;
            this.type = type;
        }

        @Override

    
    def input1
    def input2
    def input1Artifact
    def input2Artifact
    def output1
    def output2
    
    def setup() {
        applyPlugin()
        addSigningProperties()
        
        input1 = getResourceFile("1.txt")
        input1Artifact = new DefaultPublishArtifact(input1.name, "Text File", "txt", null, null, input1)

            this.inputs = inputs;
            this.ruleSourceType = ruleSourceType;
            this.ruleExtractor = ruleExtractor;
        }

        @Override
        public ModelReference<?> getSubject() {
            return targetReference;
        }

        @Override
        public List<? extends ModelReference<?>> getInputs() {
            return inputs;
        }

        @Override