如何设置 Tensorflow Lite C++ 的输入

Posted 2023-02-16

【中文标题】如何设置 Tensorflow Lite C++ 的输入

【英文标题】：how to set input of Tensorflow Lite C++

【发布时间】：2018-10-13 12:16:23

【问题描述】：

我正在尝试使用 TensorflowLite 模型测试简单的 tensorflow lite c++ 代码。 它有两个浮点数并进行异或。但是，当我更改输入时，输出不会改变。我猜interpreter->typed_tensor<float>(0)[0] = x 行是错误的，所以输入没有正确应用。我应该如何更改代码才能工作？

这是我的代码

#include <stdio.h>
#include <stdlib.h>
#include <string>
#include <vector>
#include "tensorflow/contrib/lite/kernels/register.h"
#include "tensorflow/contrib/lite/model.h"
#include "tensorflow/contrib/lite/string_util.h"
#include "tensorflow/contrib/lite/tools/mutable_op_resolver.h"

int main()
        const char graph_path[14] = "xorGate.lite";
        const int num_threads = 1;
        std::string input_layer_type = "float";
        std::vector<int> sizes = 2;
        float x,y;

        std::unique_ptr<tflite::FlatBufferModel> model(
                tflite::FlatBufferModel::BuildFromFile(graph_path));

        if(!model)
                printf("Failed to mmap model\n")
                exit(0);
        

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

        if(!interpreter)
                printf("Failed to construct interpreter\n");
                exit(0);
        
        interpreter->UseNNAPI(false);

        if(num_threads != 1)
                interpreter->SetNumThreads(num_threads);
        

        int input = interpreter->inputs()[0];
        interpreter->ResizeInputTensor(0, sizes);

        if(interpreter->AllocateTensors() != kTfLiteOk)
                printf("Failed to allocate tensors\n");
                exit(0);
        

        //read two numbers

        std::printf("Type two float numbers : ");
        std::scanf("%f %f", &x, &y);
        interpreter->typed_tensor<float>(0)[0] = x;
        interpreter->typed_tensor<float>(0)[1] = y;

        printf("hello\n");
        fflush(stdout);
        if(interpreter->Invoke() != kTfLiteOk)
                std::printf("Failed to invoke!\n");
                exit(0);
        
        float* output;
        output = interpreter->typed_output_tensor<float>(0);
        printf("output = %f\n", output[0]);
        return 0;

这是我运行代码时出现的消息。

root@localhost:/home# ./a.out 
nnapi error: unable to open library libneuralnetworks.so
Type two float numbers : 1 1
hello
output = 0.112958
root@localhost:/home# ./a.out 
nnapi error: unable to open library libneuralnetworks.so
Type two float numbers : 0 1
hello
output = 0.112958

【参考方案1】：

通过改变解决

interpreter->typed_tensor<float>(0)[0] = x;

到

interpreter->typed_input_tensor<float>(0)[0] = x;

【参考方案2】：

input var 应该有输入张量 ID。 你可以试试：

interpreter->typed_tensor<float>(input)[0] = x;