时间戳

首页 > 解决方案 > 矩阵数据数组的Tensorflow tflite c ++ api推理

c++ - 矩阵数据数组的Tensorflow tflite c ++ api推理

问题描述

我正在创建一个类，该类将用于使用 tensorflow 的 tflite c++ api 在 c++ 中的嵌入式设备（不是树莓派）上运行推理。Tensorflow 似乎没有关于如何对 n 个图像数据样本进行推理的良好文档。我在 python 中的数据形状是 (n, 5, 40, 1) [n 个样本，5 个高度，40 个宽度，1 个通道]。我无法弄清楚的是如何输入数据并在输出中接收每个样本的推断。我有两个班级，所以我应该收到 n 二维数组输出。有谁知道您是否可以传入任何数据类型，例如 Eigen？我正在使用形状 (1, 5, 2, 1) 的输入进行测试，以简化我的测试。

#include "classifier.h"
#include <iostream>

using namespace tflite;

Classifier::Classifier(std::string modelPath) {
    tflite::StderrReporter error_reporter;
    model = tflite::FlatBufferModel::BuildFromFile(modelPath.c_str(), &error_reporter);

    tflite::ops::builtin::BuiltinOpResolver resolver;
    tflite::InterpreterBuilder(*model, resolver)(&interpreter); // private class variable interpreter
    std::vector<int> sizes = {1, 5, 2, 1};
    interpreter->ResizeInputTensor(0, sizes);
    interpreter->AllocateTensors();


}

std::vector<std::vector<float> Classifier::getDataSamples() {
    std::vector<std::vector<float> test = {{0.02, 0.02}, {0.02, 0.02}, {0.02, 0.02},{0.02, 0.02},{0.02, 0.02},};
    return test;
}

float Classifier::predict() {


    std::vector<float> signatures = getDataSamples();
    for (int i = 0; i < signatures.size(); ++i) {
        interpreter->typed_input_tensor<float>(0)[i];
    }

    // float* input = interpreter->typed_input_tensor<float>(0);
    // *input = 1.0;

    interpreter->Invoke();

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

    return *output;
}

标签： c++tensorflowtensorflow-lite

解决方案

From the Tensorflow documentation we can find below details,

It should be noted that:

  • Tensors are represented by integers, in order to avoid string comparisons (and any fixed dependency on string libraries).
  • An interpreter must not be accessed from concurrent threads.
  • Memory allocation for input and output tensors must be triggered by calling AllocateTensors() right after resizing tensors.

You can find more about the Load and run a model in C++ here.

推荐阅读