Although every care has been taken to ensure that the HaynesPro WorkshopData Car Edition data is accurate and complete, no liability other than that which may not be excluded by law, can be accepted for damage, loss or injury caused by errors or omissions in the data. In no case shall the liability of the company , its distributors and agents exceed the amount you paid for HaynesPro WorkshopData Car Edition.
windows.ai.machinelearning

// Run inference var results = await session.EvaluateAsync(binding, "runId");

var result = await session.EvaluateAsync(binding, ""); var classId = result.Outputs["softmaxout"] as TensorFloat;

var session = new LearningModelSession(model, device);

var info = LearningModelDevice.FindAllDevices(); foreach (var d in info) Console.WriteLine(d.AdapterId); | Model Type | Input Shape | Output Shape | |------------|-------------|---------------| | Image classification | [1,3,224,224] | [1,1000] | | Object detection (YOLO) | [1,3,640,640] | [1,84,8400] | | BERT text | [1,128] (ids) + [1,128] (mask) | [1,2] (logits) | 7. Debugging & Performance Enable diagnostics:

// 1. Preprocess: resize to model input size (224x224) var resized = await ImageHelper.ResizeBitmap(bitmap, 224, 224); // 2. Convert to float tensor (channel-first, normalized) var tensor = ImageHelper.BitmapToTensor(resized);

// Get output var outputTensor = results.Outputs["output"] as TensorFloat; var outputArray = outputTensor.GetAsVectorView(); public async Task<string> ClassifyImage(SoftwareBitmap bitmap)

Changing the car variant will reset the cost estimate! Continue?

Select vehicle variant

Windows.ai.machinelearning May 2026

// Run inference var results = await session.EvaluateAsync(binding, "runId");

var result = await session.EvaluateAsync(binding, ""); var classId = result.Outputs["softmaxout"] as TensorFloat; windows.ai.machinelearning

var session = new LearningModelSession(model, device); // Run inference var results = await session

var info = LearningModelDevice.FindAllDevices(); foreach (var d in info) Console.WriteLine(d.AdapterId); | Model Type | Input Shape | Output Shape | |------------|-------------|---------------| | Image classification | [1,3,224,224] | [1,1000] | | Object detection (YOLO) | [1,3,640,640] | [1,84,8400] | | BERT text | [1,128] (ids) + [1,128] (mask) | [1,2] (logits) | 7. Debugging & Performance Enable diagnostics: Convert to float tensor (channel-first

// 1. Preprocess: resize to model input size (224x224) var resized = await ImageHelper.ResizeBitmap(bitmap, 224, 224); // 2. Convert to float tensor (channel-first, normalized) var tensor = ImageHelper.BitmapToTensor(resized);

// Get output var outputTensor = results.Outputs["output"] as TensorFloat; var outputArray = outputTensor.GetAsVectorView(); public async Task<string> ClassifyImage(SoftwareBitmap bitmap)