如何在C ++中为Tensorflow-Lite设置图像输入？

本文介绍了如何在C ++中为Tensorflow-Lite设置图像输入？的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述 29岁程序员，3月因学历无情被辞！ 我正在尝试将Tensoflow模型从Python + Keras版本转移到嵌入式平台上具有C ++的Tensorflow Lite。 似乎我不知道如何 输入形状应为（1、224、224、3）。 作为输入，我正在使用openCV拍摄图像，并将其转换为CV_BGR2RGB。 std :: unique_ptr< tflite :: FlatBufferModel> model_stage1 = tflite :: FlatBufferModel :: BuildFromFile（ model1.tflite）; TFLITE_MINIMAL_CHECK（model_stage1！= nullptr）; //构建解释器 tflite :: ops :: builtin :: BuiltinOpResolver resolver_stage1; std :: unique_ptr< Interpreter> interpreter_stage1; tflite :: InterpreterBuilder（* model_stage1，resolver_stage1）（& interpreter_stage1）; TFLITE_MINIMAL_CHECK（interpreter_stage1！= nullptr）; cv :: Mat cvimg = cv :: imread（imagefile）; if（cvimg.data == NULL）{ printf（ ===图片读取错误=== \n）; 返回0； } cv :: cvtColor（cvimg，cvimg，CV_BGR2RGB）; uchar * input_1 = interpreter_stage1-> typed_input_tensor< uchar>（0）; memcpy（...）; 对于此uchar类型，正确设置memcpy存在问题。 当我这样做时，我在工作中遇到段故障： memcpy （input_1，cvimg.data，cvimg.total（）* cvimg.elemSize（））; 在这种情况下应如何正确填写输入内容？解决方案要将我的评论转换为答案： Memcpy在这里可能不是正确的方法。 OpenCV将图像保存为每像素RGB顺序（或BGR或另一种颜色组合）颜色值的一维数组。可以通过以下方式遍历这些RGB块： for（const auto& rgb： cvimg）{ //现在rgb [0]为红色，rgb [1]为绿色，rgb [2]为蓝色。 } 将值写入Tensorflow-Lite typed_input_tensor应该是这样的；其中i是索引（迭代器），x是赋值： 解释器-> typed_input_tensor< ; uchar>（0）[i] = x; 所以循环看起来像这样： for（size_t i = 0; size_t< cvimg.size（）; ++ i）{ const auto& rgb = cvimg [i]; 解释器-> typed_input_tensor< uchar>（0）[3 * i + 0] = rgb [0]; 解释器-> typed_input_tensor< uchar>（0）[3 * i +1] = rgb [1]; 解释器-> typed_input_tensor< uchar>（0）[3 * i + 2] = rgb [2]; } I am trying to move our Tensoflow model from Python+Keras version to Tensorflow Lite with C++ on an embedded platform.It looks like I don't know how set properly input for interpreter.Input shape should be (1, 224, 224, 3).As an input I am taking image with openCV, converting this to CV_BGR2RGB.std::unique_ptr<tflite::FlatBufferModel> model_stage1 =tflite::FlatBufferModel::BuildFromFile("model1.tflite"); TFLITE_MINIMAL_CHECK(model_stage1 != nullptr); // Build the interpreter tflite::ops::builtin::BuiltinOpResolver resolver_stage1; std::unique_ptr<Interpreter> interpreter_stage1; tflite::InterpreterBuilder(*model_stage1, resolver_stage1)(&interpreter_stage1);TFLITE_MINIMAL_CHECK(interpreter_stage1 != nullptr); cv::Mat cvimg = cv::imread(imagefile); if(cvimg.data == NULL) { printf("=== IMAGE READ ERROR ===\n"); return 0; } cv::cvtColor(cvimg, cvimg, CV_BGR2RGB); uchar* input_1 = interpreter_stage1->typed_input_tensor<uchar>(0); memcpy( ... );I have issue with proper setup of memcpy for this uchar type.When I am doing like this, I have seg fault during working:memcpy(input_1, cvimg.data, cvimg.total() * cvimg.elemSize());How should I properly fill input in this case? 解决方案 To convert my comments into an answer:Memcpy might not be the right approach here. OpenCV saves images as 1-dimensional arrays of RGB-ordered (or BGR or yet another color combination) color values per pixel. It is possible to iterate over these RGB-chunks via:for (const auto& rgb : cvimg) { // now rgb[0] is the red value, rgb[1] green and rgb[2] blue.}And writing values to a Tensorflow-Lite typed_input_tensor should be done like this; where i is the index (iterator) and x the assigned value:interpreter->typed_input_tensor<uchar>(0)[i] = x;So the loop could look like this:for (size_t i = 0; size_t < cvimg.size(); ++i) { const auto& rgb = cvimg[i]; interpreter->typed_input_tensor<uchar>(0)[3*i + 0] = rgb[0]; interpreter->typed_input_tensor<uchar>(0)[3*i + 1] = rgb[1]; interpreter->typed_input_tensor<uchar>(0)[3*i + 2] = rgb[2];} 这篇关于如何在C ++中为Tensorflow-Lite设置图像输入？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！ 上岸，阿里云！