如何在c ++项目中使用TF Lite库

Question

过去1-2天，我一直在努力构建TensorFlow Lite，因此我可以在自己的C \ C ++项目中将其用作标头或库。

例如，我有一个main.cpp的C ++项目，其代码如下：

#include "tensorflow/lite/model.h"
#include "tensorflow/lite/interpreter.h"
#include "tensorflow/lite/kernels/register.h"

int main()
{
    std::unique_ptr<tflite::FlatBufferModel> model;
    model = tflite::FlatBufferModel::BuildFromBuffer(h5_converted_tflite, h5_converted_tflite_len);

    tflite::ops::builtin::BuiltinOpResolver resolver;
    std::unique_ptr<tflite::Interpreter> interpreter;
    tflite::InterpreterBuilder(*model, resolver)(&interpreter);

    // Resize input tensors, if desired.
    interpreter->AllocateTensors();

    float* input = interpreter->typed_input_tensor<float>(0);
    // Fill `input`.

    interpreter->Invoke();

    float* output = interpreter->typed_output_tensor<float>(0);
}

我应该从哪里下载\ build，然后从何处下载，以便可以成功地编译此代码？当前，它显然说找不到h文件，并且当我克隆TF存储库并将其添加到include文件夹时，它找不到“ flatbuffers.h”文件，而当我手动添加它时，它给出了我有很多联系错误。任何帮助将不胜感激在这里...

预先感谢

Answer 1

尝试下面的代码，该代码已通过TensorFlow lite 1.14.0测试：

std::string str = "model.tflite";
ifstream file(str, std::ifstream::binary);
file.seekg(0, file.end);
int length = file.tellg();
file.seekg(0, file.beg);
char * model_data = new char [length];
file.read (model_data, length);
file.close();
std::unique_ptr<tflite::Interpreter> interpreter;
std::unique_ptr<tflite::FlatBufferModel> model;
model = tflite::FlatBufferModel::BuildFromBuffer(model_data, length);
tflite::InterpreterBuilder(*model, resolver)(&interpreter);
interpreter->AllocateTensors();