@__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...

    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.");

  %result:4 = tf_device.replicate([%arg0, %arg1] as %input0: tensor<*xf32>) {n = 2 : i32} {
    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]]
}

// -----

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>

          absl::StrCat("tensor parsing error: ", alias));
    }

    inputs.emplace_back(feed_name, tensor);
  }

  if (!request_inputs.empty() &&
      seen_request_inputs.size() != request_inputs.size()) {
    return absl::InvalidArgumentError(absl::StrCat(
        "Inputs contains invalid name. Used request inputs: ",
        absl::StrJoin(seen_request_inputs, ","),

=== Build cycles
Gradle starts watching for changes just before a task executes.
If a task modifies its own inputs while executing, Gradle will detect the change and trigger a new build.
If every time the task executes, the inputs are modified again, the build will be triggered again.
This isn't unique to continuous build.
A task that modifies its own inputs will never be considered up-to-date when run "normally" without continuous build.

              NodeWith(Op("Add"), Name("add"),
                       Inputs(Out(NodeWith(Name("placeholder_a"))),
                              Out(NodeWith(Name("placeholder_b"))))));

  EXPECT_EQ(Explain(add.node(), NodeWith(Inputs())),
            "\nexpected 0 inputs but node has 2");
  EXPECT_EQ(
      Explain(add.node(), NodeWith(Inputs(Out(NodeWith(Name("blah"))), _))),

// Creates parameters (placeholders) in the tracing `ctx` using the shape and
// dtype of `inputs`.
Status CreateParamsForInputs(AbstractContext* ctx,
                             absl::Span<AbstractTensorHandle* const> inputs,
                             std::vector<AbstractTensorHandle*>* params);

// A callable that takes tensor inputs and returns zero or more tensor outputs.
using Model = std::function<Status(AbstractContext*,

                  const std::vector<Output>& inputs,
                  std::vector<Output>* outputs) {
  DCHECK(outputs != nullptr);
  DCHECK(outputs->empty());

  // The control dependency is analogous to that in CreateCond().
  Scope body_scope =
      scope.NewSubScope("body").WithControlDependencies(inputs[0]);
  TF_RETURN_IF_ERROR(body(body_scope, inputs, outputs));

  const size_t num_loop_vars = inputs.size();