# \#ml **URL:** https://forum.opencv.org/tag/ml/69.md [Latest](https://forum.opencv.org/latest.md) · [Categories](https://forum.opencv.org/categories.md) · [Tags](https://forum.opencv.org/tags.md) --- ## [Seeking advice: self-training workflow for small object counting (2K camera, no pretrained models)](https://forum.opencv.org/t/seeking-advice-self-training-workflow-for-small-object-counting-2k-camera-no-pretrained-models/24142)
**Author:** [@Exto\_Logia](https://forum.opencv.org/u/Exto_Logia)\ **Replies:** 1\ **Last updated:** [October 24, 2025, 5:50pm UTC](https://forum.opencv.org/t/seeking-advice-self-training-workflow-for-small-object-counting-2k-camera-no-pretrained-models/24142 "2025-10-24T17:50:40Z")
I’m new in OpenCV and currently working on an object counting system using a 2K camera, but I’m not using any pretrained models or machine learning yet. My current pipeline is fully classical — it relies on OpenCV filter… --- ## [Issue when training the ML model](https://forum.opencv.org/t/issue-when-training-the-ml-model/19824)
**Author:** [@Tin\_Basic](https://forum.opencv.org/u/Tin_Basic)\ **Replies:** 1\ **Last updated:** [January 28, 2025, 5:57pm UTC](https://forum.opencv.org/t/issue-when-training-the-ml-model/19824 "2025-01-28T17:57:59Z")
Working on a model that recognizes handwritten digits from the MNIST dataset. Did my code in visual studio. After training the data i get Nan and inf in the output layer everytime. std::string fileNameImages = file… --- ## [How to save SVM models trained by python and use it Android for prediction?](https://forum.opencv.org/t/how-to-save-svm-models-trained-by-python-and-use-it-android-for-prediction/15862)
**Author:** [@Ranjit\_kw](https://forum.opencv.org/u/Ranjit_kw)\ **Replies:** 3\ **Last updated:** [December 15, 2023, 8:44am UTC](https://forum.opencv.org/t/how-to-save-svm-models-trained-by-python-and-use-it-android-for-prediction/15862 "2023-12-15T08:44:27Z")
\# define svm classifier model model = SVC(kernel='linear', probability=True) model.fit(face\_embd, labels) how to save it and use it on android kotlin --- ## [Using a MLP to classify lists of numbers](https://forum.opencv.org/t/using-a-mlp-to-classify-lists-of-numbers/13286)
**Author:** [@tamirmichael](https://forum.opencv.org/u/tamirmichael)\ **Replies:** 7\ **Last updated:** [May 24, 2023, 5:37pm UTC](https://forum.opencv.org/t/using-a-mlp-to-classify-lists-of-numbers/13286 "2023-05-24T17:37:17Z")
Hello and thank you for taking the time, This is my very first attempt to work with neural networks after reading some theory about them. What I am trying to do is to classify long lists of numbers (600+ of them per tr… --- ## [Prediction result shares no similarity with training data](https://forum.opencv.org/t/prediction-result-shares-no-similarity-with-training-data/13260)
**Author:** [@Shassk](https://forum.opencv.org/u/Shassk)\ **Replies:** 10\ **Last updated:** [May 22, 2023, 1:22pm UTC](https://forum.opencv.org/t/prediction-result-shares-no-similarity-with-training-data/13260 "2023-05-22T13:22:39Z")
I am trying to use an MLP for classification (yes, I’m aware of dnn, but now I’m interested in ml) so I put together a simple example to test things with a simple formula: array of classId / classesCount values =\> zero-f… --- ## [Deploy LBPHFaceRecognizer model without images](https://forum.opencv.org/t/deploy-lbphfacerecognizer-model-without-images/12635)
**Author:** [@yoko911](https://forum.opencv.org/u/yoko911)\ **Replies:** 2\ **Last updated:** [April 1, 2023, 2:20pm UTC](https://forum.opencv.org/t/deploy-lbphfacerecognizer-model-without-images/12635 "2023-04-01T14:20:18Z")
So I have trained a LBPHFaceRecognizer model using the CSV examples in the opencv documentation, is there a way to get the nodes/coefficients from the trained model and then apply them? I just don’t want to load or even… --- ## [Symbol recognition is very poor, not sure why](https://forum.opencv.org/t/symbol-recognition-is-very-poor-not-sure-why/12441)
**Author:** [@FatCat](https://forum.opencv.org/u/FatCat)\ **Replies:** 5\ **Last updated:** [March 22, 2023, 7:41am UTC](https://forum.opencv.org/t/symbol-recognition-is-very-poor-not-sure-why/12441 "2023-03-22T07:41:17Z")
Hi! I’m new to using OpenCV and I used this short tutorial for KNN character recognition. OpenCV 3 KNN Character Recognition C++ - YouTube I switched out the image used for training for one with custom drawn symbols. Ho… --- ## [2D Dataset Classifikation with HaarCascade](https://forum.opencv.org/t/2d-dataset-classifikation-with-haarcascade/11754)
**Author:** [@trausch](https://forum.opencv.org/u/trausch)\ **Replies:** 2\ **Last updated:** [January 25, 2023, 8:32pm UTC](https://forum.opencv.org/t/2d-dataset-classifikation-with-haarcascade/11754 "2023-01-25T20:32:05Z")
I want to teach a 2D data set. Is that possible? Background: I have a function curve y=f(x) and would like to have the resulting y (or its derivative) assigned to certain, fixed classes . I have only found examples for 3… --- ## [How to use cv::ml::Boost for a regression problem?](https://forum.opencv.org/t/how-to-use-cv-boost-for-a-regression-problem/11654)
**Author:** [@Olena\_Ivina](https://forum.opencv.org/u/Olena_Ivina)\ **Replies:** 0\ **Last updated:** [January 17, 2023, 2:40pm UTC](https://forum.opencv.org/t/how-to-use-cv-boost-for-a-regression-problem/11654 "2023-01-17T14:40:57Z")
The OpenCv documentation says that: class cv::ml::Boost - Boosted tree classifier derived from DTrees class cv::ml::RTrees - The class implements the random forest predictor With the RTrees I received correct predic… --- ## [OpenCV random forest parallelization](https://forum.opencv.org/t/opencv-random-forest-parallelization/10478)
**Author:** [@p-leroy](https://forum.opencv.org/u/p-leroy)\ **Replies:** 0\ **Last updated:** [October 7, 2022, 2:04pm UTC](https://forum.opencv.org/t/opencv-random-forest-parallelization/10478 "2022-10-07T14:04:55Z")
I have read the sources of OpenCV and it seems like the random forest implementation is not parallelized. Is it really the case? And if yes, is there a specific reason why the random forest has not been parallelized? Th… --- ## [What do the values returned from cv::ml::StatModel::predict() when using the RAW\_OUTPUT flag represent?](https://forum.opencv.org/t/what-do-the-values-returned-from-cv-predict-when-using-the-raw-output-flag-represent/8449)
**Author:** [@snsc](https://forum.opencv.org/u/snsc)\ **Replies:** 1\ **Last updated:** [April 20, 2022, 8:33am UTC](https://forum.opencv.org/t/what-do-the-values-returned-from-cv-predict-when-using-the-raw-output-flag-represent/8449 "2022-04-20T08:33:45Z")
I’m using an SVM to predict if images are of one label or another. I wanted to get some more information from the cv::ml::StatModel::predict method, so I used the RAW\_OUTPUT flag to get some value other than just the pre… --- ## [Calculate slope and bias of linear decision function \[SVM\]](https://forum.opencv.org/t/calculate-slope-and-bias-of-linear-decision-function-svm/4982)
**Author:** [@lando\_k](https://forum.opencv.org/u/lando_k)\ **Replies:** 0\ **Last updated:** [August 30, 2021, 2:17pm UTC](https://forum.opencv.org/t/calculate-slope-and-bias-of-linear-decision-function-svm/4982 "2021-08-30T14:17:23Z")
Hi all, for my project I need to get the exact parameters of the decision function calculated by the SVM. Right now, I’m struggling to understand the output of the methods getDecisionFunction() and getUncompressedSuppo… --- ## [Boost training issue: vector subscript out of range](https://forum.opencv.org/t/boost-training-issue-vector-subscript-out-of-range/3737)
**Author:** [@dporto](https://forum.opencv.org/u/dporto)\ **Replies:** 5\ **Last updated:** [June 18, 2021, 2:53pm UTC](https://forum.opencv.org/t/boost-training-issue-vector-subscript-out-of-range/3737 "2021-06-18T14:53:15Z")
I am having trouble with training a Boosted trees model for regression. I am using the code below to train the model, but get a runtime error for “vector subscript out of range” Ptr\ trainingData = TrainData::… --- ## [Random Forest setting random seed](https://forum.opencv.org/t/random-forest-setting-random-seed/3733)
**Author:** [@dporto](https://forum.opencv.org/u/dporto)\ **Replies:** 3\ **Last updated:** [June 9, 2021, 2:42pm UTC](https://forum.opencv.org/t/random-forest-setting-random-seed/3733 "2021-06-09T14:42:46Z")
Since there is randomness involved in the computation of a random forest classifier, it is necessary to define a random seed to get reproducible results. Is this possible to do in the current implementation of the algori… --- ## [Attempt at an artwork classifier using a bag of visual words model keeps predicting the same class](https://forum.opencv.org/t/attempt-at-an-artwork-classifier-using-a-bag-of-visual-words-model-keeps-predicting-the-same-class/3618)
**Author:** [@Palves](https://forum.opencv.org/u/Palves)\ **Replies:** 2\ **Last updated:** [June 1, 2021, 7:38am UTC](https://forum.opencv.org/t/attempt-at-an-artwork-classifier-using-a-bag-of-visual-words-model-keeps-predicting-the-same-class/3618 "2021-06-01T07:38:35Z")
I’m trying to do a classifier for artwork using a bag of visual words model. However, I keep getting the same prediction for every artwork I feed into it. It seems like it keeps predicting the most repeated class in the … --- ## [From ANN\_MLP to dnn](https://forum.opencv.org/t/from-ann-mlp-to-dnn/2080)
**Author:** [@ffolch](https://forum.opencv.org/u/ffolch)\ **Replies:** 6\ **Last updated:** [March 11, 2021, 2:33pm UTC](https://forum.opencv.org/t/from-ann-mlp-to-dnn/2080 "2021-03-11T14:33:40Z")
I’d like to execute an ANN\_MLP on GPU I think it’s not possible, isn’t it? So, I’d like to create automatically a neuroan network based on dnn module, from the module file that contains the trained model and its arquit… --- ## [Any recommendations for video (motion-based) machine-learning?](https://forum.opencv.org/t/any-recommendations-for-video-motion-based-machine-learning/1460)
**Author:** [@Charles\_R](https://forum.opencv.org/u/Charles_R)\ **Replies:** 2\ **Last updated:** [February 13, 2021, 2:50am UTC](https://forum.opencv.org/t/any-recommendations-for-video-motion-based-machine-learning/1460 "2021-02-13T02:50:30Z")
I have been looking into machine learning tools for a while, esp. pyTorch and scikitlearn and want to use them for object identification. All the resources I have found so far, however, deal with image recognition rather… --- ## [Segmentation fault](https://forum.opencv.org/t/segmentation-fault/1260)
**Author:** [@Jan\_Hackenberg](https://forum.opencv.org/u/Jan_Hackenberg)\ **Replies:** 1\ **Last updated:** [February 1, 2021, 9:11pm UTC](https://forum.opencv.org/t/segmentation-fault/1260 "2021-02-01T21:11:08Z")
I am trying to execute based on example code: using namespace cv; using namespace cv::ml; // mat is a Mat containing the features computed beforehand Ptr\ model = EM::create(); model-\>setClustersNumber(stat…