Append multiple VNCoreMLModel ARKit and CoreML - swift

Question

I'm a noob and I don't really know how can I happened multiple CoreML model to the VNCoreMLRequest.
With the code below is just using one model but I want to append also another model (visionModel2 on the example below). Can anyone help me? Thank you!
private func performVisionRequest(pixelBuffer: CVPixelBuffer){
let visionModel = try! VNCoreMLModel(for: self.iFaceModel.model)
let visionModel2 = try! VNCoreMLModel(for: self.ageModel.model)
let request = VNCoreMLRequest(model: visionModel){ request, error in
if error != nil {
return
}
guard let observations = request.results else {
return
}
let observation = observations.first as! VNClassificationObservation
print("Name \(observation.identifier) and confidence is \(observation.confidence)")
DispatchQueue.main.async {
if observation.confidence.isLess(than: 0.04) {
self.displayPredictions(text: "Not recognized")
print("Hidden")
}else {
self.displayPredictions(text: observation.identifier)
}
}
}

Answer 1

To evaluate an image using multiple ML models, you’ll need to perform multiple requests. For example:
let faceModelRequest = VNCoreMLRequest(model: visionModel)
let ageModelRequest = VNCoreMLRequest(model: visionModel2)
let handler = VNImageRequestHandler( /* my image and options */ )
handler.perform([faceModelRequest, ageModelRequest])
guard let faceResults = faceModelRequest.results as? [VNClassificationObservation],
let ageResults = ageModelRequest.results as? [VNClassificationObservation]
else { /*handle errors from each request */ }
(Yes, you can run Vision requests without a completion handler and then collect the results from multiple requests. Might want to check prefersBackgroundProcessing on the requests and dispatch everything to a background queue yourself, though.)
After that, you probably want to iterate the results from both requests together. Here’s a handy way you could do that with Swift standard library sequence functions, but it assumes that both models return information about the same faces in the same order:
for (faceObservation, ageObservation) in zip (faceResults, ageResults) {
print(“face \(faceObservation.classification) confidence \(faceObservation.confidence)”)
print(“age \(ageObservation.classification) confidence \(ageObservation.confidence)”)
// whatever else you want to do with results...
}
Disclaimer: Code written in StackExchange iOS app, not tested. But it’s at least a sketch of what you’re probably looking for — tweak as needed.