Stack Overflow
Stack Overflow

Questions tagged [windows-machine-learning]

Windows ML is a API for evaluating trained machine learning models locally in Windows 10 applications.

Windows ML is a API for evaluating trained machine learning models locally in Windows apps (C#, C++, and JavaScript), including GPU acceleration if hardware is available. Models are in ONNX format. Available for UWP apps since Windows 10 build 17723, see Windows ML docs

53 questions
1
vote
1 answer

How to resize VideoFrame or ImageFeatureValue to specific size to match input shape requirements?

My goal is to use tinyYolov3 model to perform object detection in real-time through the HoloLens. I want to incorporate the model as an ONNX file directly in the project and to compute the predictions inside the HoloLens itself. In order to do so, I…
OD4ZeWin
  • 31
  • 2
1
vote
2 answers

ONNX model with sub operator error does not bind

I am trying to create a session with a squeezenet ONNX model using: session = winrt::Windows::AI::MachineLearning::LearningModelSession{ model, winrt::Windows::AI::MachineLearning::LearningModelDevice(deviceKind) }; I have two versions of…
user3413491
  • 31
  • 3
1
vote
1 answer

Windows.AI.MachineLearning.Preview - loading model from stream throws exception

I'm integrating WindowsML neural network inference into a project targeting Windows 10 (Windows SDK version 17134). Loading model from file works fine, as well as other inference steps. But loading model from stream consistently throws…
k.v.
  • 1,193
  • 8
  • 11
1
vote
1 answer

windows-machine-learning - "No suitable kernel definition found for op Add"

Running latest WinMLRunning but getting error: No suitable kernel definition found for op Add (node InceptionV1/InceptionV1/Conv2d_1a_7x7/BatchNorm/FusedBatchNorm) I converted custom inference frozen Inception model to ONNX using VS or mmdnn. I'm…
ms2579
  • 11
  • 2
1
vote
1 answer

Cannot find the ONNX file specified using WinML

I am trying to load an ONNX model using WinML, with the following code: private async Task InitializeModelAsync() { var path = @"ms-appx:///Assets/FER-Emotion-Recognition.onnx"; var file = await StorageFile.GetFileFromApplicationUriAsync(new…
Justin XL
  • 38,763
  • 7
  • 88
  • 133
0
votes
0 answers

How to detect target object's offset from a reference point?

How to detect a target object's offset from aa reference point in an image using .NET Machine Learning? For example, let's say I have five images (1,2,3,4,5). these images have a ball in it (the ball is the target object). Image-1 is the "reference…
coJade
  • 1
  • 1
0
votes
0 answers

No extension for "Windows Machine Learning Code Generator" in vs 2022

I am looking for Windows Machine Learning Code Generator with VS 2022 supports but in market place no option available. I am able to find it for VS 2019 but nothing related to vs2022. How to use it with vs2022 with ONNX model? Or any workaround…
Sheepu Kumar
  • 1
0
votes
0 answers

How to bind a onnx dynamic output in C++/WinRT using LearningModelBinding?

I have a onnx model of detectronV2 that has outputs that are not of a fixed size, they are dynamic. I was able to do inference in python with the onnxruntime: import onnxruntime # Initialize session and get prediction model_path =…
Anna Maule
  • 268
  • 1
  • 9
0
votes
0 answers

Windows.AI.MachineLearning incorrect parameter with Conv3DTranspose

I'm getting the following error when trying to run inference using an ONNX model using the Windows.AI.MachineLearning package in a UWP app. 'The parameter is incorrect. Non-zero status code returned while running Node:…
Alton
  • 1
0
votes
0 answers

How to add learning capability for TextPredictionGenerator?

How to make TextPredictionGenerator support learning from user input? https://learn.microsoft.com/en-us/uwp/api/windows.data.text.textpredictiongenerator?view=winrt-22621
brook hong
  • 573
  • 6
  • 13
0
votes
0 answers

Windows ML for Visual studio 2013?

I have implemented the Windows ML app in C++ with Visual Studio (VS) 2019 and 2022. I would like to migrate it to VS 2013. Is it possible?. Under prequisites it says it only works with VS2019 or VS2017 and higher on the website here
Varun
  • 1
  • 1
0
votes
1 answer

System.AccessViolationException at newing LearningModelSession (using GPU mode)

everyone! I am trying to make an inferencing app based of SnapCandy Sample of Windows-Machine-Learning github. My ONNX Model file is exported at pytorch 1.10. Onnx format : v4, opset v9 Windows version : Win10 21H2 (Build# 19044.1466) Graphics :…
mathto
  • 1
0
votes
1 answer

How to create a TensorFloat for a shape that has unknown component?

I have followed this example to bind input and output to a ONNX model. // I can bind this shape fine since it has all known components: std::vector shape({ 1, 1000, 1, 1 }); binding.Bind(L"softmaxout_1",…
lq_msu
  • 73
  • 1
  • 4
0
votes
1 answer

Difference between Tensorfloat and ImageFeatureValue

When using the Windows-Machine-Learning library, the input and output to the onnx models is often either TensorFloat or ImageFeatureValue format. My question: What is the difference between these? It seems like I am able to change the form of the…
chris
  • 82
  • 7
0
votes
1 answer

Access TensorFloat data

I am using Windows-Machine-Learning to convert my VideoFrame to a TensorFloat _input (shape: 1,3,256,192; RGB channels + image), load that into my onnx model and receive as _output another TensorFloat object (shape: 1,17,64,48; 17 detected objects +…
chris
  • 82
  • 7
1
2
3 4