Como implementar um delegado personalizado

// MyDelegate implements the interface of SimpleDelegateInterface.
// This holds the Delegate capabilities.
class MyDelegate : public SimpleDelegateInterface {
 public:
  bool IsNodeSupportedByDelegate(const TfLiteRegistration* registration,
                                 const TfLiteNode* node,
                                 TfLiteContext* context) const override {
    // Only supports Add and Sub ops.
    if (kTfLiteBuiltinAdd != registration->builtin_code &&
        kTfLiteBuiltinSub != registration->builtin_code)
      return false;
    // This delegate only supports float32 types.
    for (int i = 0; i < node->inputs->size; ++i) {
      auto& tensor = context->tensors[node->inputs->data[i]];
      if (tensor.type != kTfLiteFloat32) return false;
    }
    return true;
  }

  TfLiteStatus Initialize(TfLiteContext* context) override { return kTfLiteOk; }

  const char* Name() const override {
    static constexpr char kName[] = "MyDelegate";
    return kName;
  }

  std::unique_ptr<SimpleDelegateKernelInterface> CreateDelegateKernelInterface()
      override {
    return std::make_unique<MyDelegateKernel>();
  }
};

// My delegate kernel.
class MyDelegateKernel : public SimpleDelegateKernelInterface {
 public:
  TfLiteStatus Init(TfLiteContext* context,
                    const TfLiteDelegateParams* params) override {
    // Save index to all nodes which are part of this delegate.
    inputs_.resize(params->nodes_to_replace->size);
    outputs_.resize(params->nodes_to_replace->size);
    builtin_code_.resize(params->nodes_to_replace->size);
    for (int i = 0; i < params->nodes_to_replace->size; ++i) {
      const int node_index = params->nodes_to_replace->data[i];
      // Get this node information.
      TfLiteNode* delegated_node = nullptr;
      TfLiteRegistration* delegated_node_registration = nullptr;
      TF_LITE_ENSURE_EQ(
          context,
          context->GetNodeAndRegistration(context, node_index, &delegated_node,
                                          &delegated_node_registration),
          kTfLiteOk);
      inputs_[i].push_back(delegated_node->inputs->data[0]);
      inputs_[i].push_back(delegated_node->inputs->data[1]);
      outputs_[i].push_back(delegated_node->outputs->data[0]);
      builtin_code_[i] = delegated_node_registration->builtin_code;
    }
    return kTfLiteOk;
  }

  TfLiteStatus Prepare(TfLiteContext* context, TfLiteNode* node) override {
    return kTfLiteOk;
  }

  TfLiteStatus Eval(TfLiteContext* context, TfLiteNode* node) override {
    // Evaluate the delegated graph.
    // Here we loop over all the delegated nodes.
    // We know that all the nodes are either ADD or SUB operations and the
    // number of nodes equals ''inputs_.size()'' and inputs[i] is a list of
    // tensor indices for inputs to node ''i'', while outputs_[i] is the list of
    // outputs for node
    // ''i''. Note, that it is intentional we have simple implementation as this
    // is for demonstration.

    for (int i = 0; i < inputs_.size(); ++i) {
      // Get the node input tensors.
      // Add/Sub operation accepts 2 inputs.
      auto& input_tensor_1 = context->tensors[inputs_[i][0]];
      auto& input_tensor_2 = context->tensors[inputs_[i][1]];
      auto& output_tensor = context->tensors[outputs_[i][0]];
      TF_LITE_ENSURE_EQ(
          context,
          ComputeResult(context, builtin_code_[i], &input_tensor_1,
                        &input_tensor_2, &output_tensor),
          kTfLiteOk);
    }
    return kTfLiteOk;
  }

 private:
  // Computes the result of addition of 'input_tensor_1' and 'input_tensor_2'
  // and store the result in 'output_tensor'.
  TfLiteStatus ComputeResult(TfLiteContext* context, int builtin_code,
                             const TfLiteTensor* input_tensor_1,
                             const TfLiteTensor* input_tensor_2,
                             TfLiteTensor* output_tensor) {
    if (NumElements(input_tensor_1) != NumElements(input_tensor_2) ||
        NumElements(input_tensor_1) != NumElements(output_tensor)) {
      return kTfLiteDelegateError;
    }
    // This code assumes no activation, and no broadcasting needed (both inputs
    // have the same size).
    auto* input_1 = GetTensorData<float>(input_tensor_1);
    auto* input_2 = GetTensorData<float>(input_tensor_2);
    auto* output = GetTensorData<float>(output_tensor);
    for (int i = 0; i < NumElements(input_tensor_1); ++i) {
      if (builtin_code == kTfLiteBuiltinAdd)
        output[i] = input_1[i] + input_2[i];
      else
        output[i] = input_1[i] - input_2[i];
    }
    return kTfLiteOk;
  }

  // Holds the indices of the input/output tensors.
  // inputs_[i] is list of all input tensors to node at index 'i'.
  // outputs_[i] is list of all output tensors to node at index 'i'.
  std::vector<std::vector<int>> inputs_, outputs_;
  // Holds the builtin code of the ops.
  // builtin_code_[i] is the type of node at index 'i'
  std::vector<int> builtin_code_;
};

// Returns default options for DummyDelegate.
DummyDelegateOptions TfLiteDummyDelegateOptionsDefault();

// Creates a new delegate instance that need to be destroyed with
// `TfLiteDummyDelegateDelete` when delegate is no longer used by TFLite.
// When `options` is set to `nullptr`, the above default values are used:
TfLiteDelegate* TfLiteDummyDelegateCreate(const DummyDelegateOptions* options);

// Destroys a delegate created with `TfLiteDummyDelegateCreate` call.
void TfLiteDummyDelegateDelete(TfLiteDelegate* delegate);

class DummyDelegateProvider : public DelegateProvider {
 public:
  DummyDelegateProvider() {
    default_params_.AddParam("use_dummy_delegate",
                             ToolParam::Create<bool>(false));
  }

  std::vector<Flag> CreateFlags(ToolParams* params) const final;

  void LogParams(const ToolParams& params) const final;

  TfLiteDelegatePtr CreateTfLiteDelegate(const ToolParams& params) const final;

  std::string GetName() const final { return "DummyDelegate"; }
};
REGISTER_DELEGATE_PROVIDER(DummyDelegateProvider);

std::vector<Flag> DummyDelegateProvider::CreateFlags(ToolParams* params) const {
  std::vector<Flag> flags = {CreateFlag<bool>("use_dummy_delegate", params,
                                              "use the dummy delegate.")};
  return flags;
}

void DummyDelegateProvider::LogParams(const ToolParams& params) const {
  TFLITE_LOG(INFO) << "Use dummy test delegate : ["
                   << params.Get<bool>("use_dummy_delegate") << "]";
}

TfLiteDelegatePtr DummyDelegateProvider::CreateTfLiteDelegate(
    const ToolParams& params) const {
  if (params.Get<bool>("use_dummy_delegate")) {
    auto default_options = TfLiteDummyDelegateOptionsDefault();
    return TfLiteDummyDelegateCreateUnique(&default_options);
  }
  return TfLiteDelegatePtr(nullptr, [](TfLiteDelegate*) {});
}

#### The following are for using the dummy test delegate in TFLite tooling ####
cc_library(
    name = "dummy_delegate_provider",
    srcs = ["dummy_delegate_provider.cc"],
    copts = tflite_copts(),
    deps = [
        ":dummy_delegate",
        "//tensorflow/lite/tools/delegates:delegate_provider_hdr",
    ],
    alwayslink = 1, # This is required so the optimizer doesn't optimize the library away.
)

cc_binary(
    name = "benchmark_model_plus_dummy_delegate",
    copts = tflite_copts(),
    linkopts = task_linkopts(),
    deps = [
        ":dummy_delegate_provider",
        "//tensorflow/lite/tools/benchmark:benchmark_model_main",
    ],
)

cc_binary(
    name = "inference_diff_plus_dummy_delegate",
    copts = tflite_copts(),
    linkopts = task_linkopts(),
    deps = [
        ":dummy_delegate_provider",
        "//tensorflow/lite/tools/evaluation/tasks:task_executor_main",
        "//tensorflow/lite/tools/evaluation/tasks/inference_diff:run_eval_lib",
    ],
)

cc_binary(
    name = "imagenet_classification_eval_plus_dummy_delegate",
    copts = tflite_copts(),
    linkopts = task_linkopts(),
    deps = [
        ":dummy_delegate_provider",
        "//tensorflow/lite/tools/evaluation/tasks:task_executor_main",
        "//tensorflow/lite/tools/evaluation/tasks/imagenet_image_classification:run_eval_lib",
    ],
)

cc_binary(
    name = "coco_object_detection_eval_plus_dummy_delegate",
    copts = tflite_copts(),
    linkopts = task_linkopts(),
    deps = [
        ":dummy_delegate_provider",
        "//tensorflow/lite/tools/evaluation/tasks:task_executor_main",
        "//tensorflow/lite/tools/evaluation/tasks/coco_object_detection:run_eval_lib",
    ],
)

TfLiteDelegate* CreateDummyDelegateFromOptions(char** options_keys,
                                               char** options_values,
                                               size_t num_options) {
  DummyDelegateOptions options = TfLiteDummyDelegateOptionsDefault();

  // Parse key-values options to DummyDelegateOptions.
  // You can achieve this by mimicking them as command-line flags.
  std::unique_ptr<const char*> argv =
      std::unique_ptr<const char*>(new const char*[num_options + 1]);
  constexpr char kDummyDelegateParsing[] = "dummy_delegate_parsing";
  argv.get()[0] = kDummyDelegateParsing;

  std::vector<std::string> option_args;
  option_args.reserve(num_options);
  for (int i = 0; i < num_options; ++i) {
    option_args.emplace_back("--");
    option_args.rbegin()->append(options_keys[i]);
    option_args.rbegin()->push_back('=');
    option_args.rbegin()->append(options_values[i]);
    argv.get()[i + 1] = option_args.rbegin()->c_str();
  }

  // Define command-line flags.
  // ...
  std::vector<tflite::Flag> flag_list = {
      tflite::Flag::CreateFlag(...),
      ...,
      tflite::Flag::CreateFlag(...),
  };

  int argc = num_options + 1;
  if (!tflite::Flags::Parse(&argc, argv.get(), flag_list)) {
    return nullptr;
  }

  return TfLiteDummyDelegateCreate(&options);
}

#ifdef __cplusplus
extern "C" {
#endif  // __cplusplus

// Defines two symbols that need to be exported to use the TFLite external
// delegate. See tensorflow/lite/delegates/external for details.
TFL_CAPI_EXPORT TfLiteDelegate* tflite_plugin_create_delegate(
    char** options_keys, char** options_values, size_t num_options,
    void (*report_error)(const char*)) {
  return tflite::tools::CreateDummyDelegateFromOptions(
      options_keys, options_values, num_options);
}

TFL_CAPI_EXPORT void tflite_plugin_destroy_delegate(TfLiteDelegate* delegate) {
  TfLiteDummyDelegateDelete(delegate);
}

#ifdef __cplusplus
}
#endif  // __cplusplus

cc_binary(
    name = "dummy_external_delegate.so",
    srcs = [
        "external_delegate_adaptor.cc",
    ],
    linkshared = 1,
    linkstatic = 1,
    deps = [
        ":dummy_delegate",
        "//tensorflow/lite/c:common",
        "//tensorflow/lite/tools:command_line_flags",
        "//tensorflow/lite/tools:logging",
    ],
)