# Yolov5 image classification in C++

**URL:** <https://forum.opencv.org/t/yolov5-image-classification-in-c/11578>\
**Category:** C++\
**Tags:** dnn, cuda\
**Created:** [January 11, 2023, 7:37am UTC](https://forum.opencv.org/t/yolov5-image-classification-in-c/11578 "2023-01-11T07:37:22Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mehrdad\_Mazhari](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/mehrdad_mazhari/32/6927_2.png) [@Mehrdad\_Mazhari](https://forum.opencv.org/u/Mehrdad_Mazhari)\
**Post date:** [January 11, 2023, 7:37am UTC](https://forum.opencv.org/t/yolov5-image-classification-in-c/11578/1 "2023-01-11T07:37:23Z")

</div>

Hi, I’ve exported yolov5-cls model to ONNX and I would like to infer on the Open-Cv C++ side.I wrote this part but the result is not correct. Could you guide me?

```
int inpWidth = 224;
int inpHeight = 224;
std::string modelFilepath{
    "model.onnx" };
std::string imageFilepath{ "18836.jpg" };

cv::Mat image = cv::imread(imageFilepath, cv::ImreadModes::IMREAD_COLOR);

cv::resize(image, image, cv::Size(inpWidth, inpHeight));

cv::Mat blob;
cv::Scalar mean{ 0.4151, 0.3771, 0.4568 };
cv::Scalar std{ 0.2011, 0.2108, 0.1896 };
bool swapRB = false;
bool crop = false;
cv::dnn::blobFromImage(image, blob, 1.0, cv::Size(inpWidth, inpHeight), mean, swapRB, crop);
if (std.val[0] != 0.0 && std.val[1] != 0.0 && std.val[2] != 0.0) {
    cv::divide(blob, std, blob);
}

cv::dnn::Net net = cv::dnn::readNetFromONNX(modelPath);
net.setInput(blob);
cv::Mat prob = net.forward();
std::cout << prob << std::endl;

cv::Mat probReshaped = prob.reshape(1, prob.total() * prob.channels());
std::vector<float> probVec =
    probReshaped.isContinuous() ? probReshaped : probReshaped.clone();
std::vector<float> probNormalized = sigmoid_(probVec);

cv::Point classIdPoint;
double confidence;
minMaxLoc(prob.reshape(1, 1), 0, &confidence, 0, &classIdPoint);
int classId = classIdPoint.x;
std::cout << " ID " << classId << " - " << " confidence "
    << confidence << std::endl;

std::vector<float> res;
float sum = 0.0f;
float t;
for (int i = 0; i < probVec.size(); i++) {
    auto sec = probVec[i];
    if (sec > 0) {
        t = expf(sec);
        res.push_back(t);
        sum += t;
    }
}
for (int i = 0; i < res.size(); i++) {
    res[i] /= sum;
}
const int topk = std::min(5, (int)res.size());

for (size_t i = 0; i < topk; ++i) {
    const auto& conf = res[i];
    std::cout << " ID " << i << " - " << " confidence "
        << conf << std::endl;
}

```

Thanks

---

<div class="post-metadata">

**Author:** ![berak](https://avatars.discourse-cdn.com/v4/letter/b/85f322/32.png) [@berak](https://forum.opencv.org/u/berak)\
**Post date:** [January 11, 2023, 9:14am UTC](https://forum.opencv.org/t/yolov5-image-classification-in-c/11578/2 "2023-01-11T09:14:56Z")

</div>

> [@Mehrdad\_Mazhari](#):
>
> yolov5-cls

so, you’re basically trying [to port this](https://github.com/ultralytics/yolov5/blob/master/classify/predict.py) to dnn / c++ ?

(didn’t even know, they had _classification_ models now …)

and, btw, your mean/std values are in [0…1], while the img is [0…255]

if i print out the [`ìm` from predict.py](https://github.com/ultralytics/yolov5/blob/master/classify/predict.py#L110)(for bus.jpg), i get:

```auto

im tensor([[[0.17681, 0.07406, 2.00916, ..., 0.99880, 1.01593, 0.99880],
         [-1.12467, 1.59817, 0.51931, ..., 1.01593, 1.03305, 1.03305],
         [1.42692, 1.05018, -0.18281, ..., 0.99880, 1.03305, 1.03305],
         ...,
         [2.04341, 2.09479, 1.25567, ..., -0.52530, -0.37118, -0.81642],
         [1.75229, 2.11191, 1.73517, ..., -1.14179, -0.54243, -0.97055],
         [1.71804, 1.44404, 1.76942, ..., -0.86780, -0.35405, 0.60493]],

```

look here:

> <https://github.com/ultralytics/yolov5/blob/cdd804d39ff84b413bde36a84006f51769b6043b/utils/augmentations.py#L347>

, imo you need to better adapt your preprocessing

---

<div class="post-metadata">

**Author:** ![berak](https://avatars.discourse-cdn.com/v4/letter/b/85f322/32.png) [@berak](https://forum.opencv.org/u/berak)\
**Post date:** [January 11, 2023, 2:04pm UTC](https://forum.opencv.org/t/yolov5-image-classification-in-c/11578/3 "2023-01-11T14:04:51Z")

</div>

> [@Mehrdad\_Mazhari](#):
>
> ```auto
> for (size_t i = 0; i < topk; ++i) {
> const auto& conf = res[i];
> std::cout << " ID " << i << " - " << " confidence "
> << conf << std::endl;
> }
> 
> ```

also, these are the _first_ 5 results, not the _5 top_ ones, which would require some sorting