Hello everybody,
For the past week I have been struggling to run inference on a classifier I built using Google's AutoML Vision tool.
At first I thought everything would go smoothly because Google allows to export a CoreML version of the final model. I assumed I would only need to use Apple's CoreML library to make it work. When I export the model Google provides a .mlmodel file and a dict.txt file with the classification labels. For the current model I have 100 labels.
This is my Swift code to run inference on the model.
private lazy var classificationRequest: VNCoreMLRequest = {
				do {
						let classificationModel = try VNCoreMLModel(for: NewGenusModel().model)
						let request = VNCoreMLRequest(model: classificationModel, completionHandler: { [weak self] request, error in
								self?.processClassifications(for: request, error: error)
						})
						request.imageCropAndScaleOption = .scaleFit
						return request
				}
				catch {
						fatalError("Error! Can't use Model.")
				}
		}()
		func classifyImage(receivedImage: UIImage) {
				let orientation = CGImagePropertyOrientation(rawValue: UInt32(receivedImage.imageOrientation.rawValue))
				if let image = CIImage(image: receivedImage) {
						DispatchQueue.global(qos: .userInitiated).async {
								let handler = VNImageRequestHandler(ciImage: image, orientation: orientation!)
								do {
										try handler.perform([self.classificationRequest])
								}
								catch {
										fatalError("Error classifying image!")
								}
						}
				}
		}
The problem started when I tried to pass a UIImage to run inference on the model. The input type of the original model was MultiArray (Float32 1 x 224 x 224 x 3). Using Coremltools library I was able to convert the input type to Image (Color 224 x 224) using Python.
This worked and here is my code:
import coremltools
import coremltools.proto.FeatureTypes_pb2 as ft
spec = coremltools.utils.load_spec("model.mlmodel")
input = spec.description.input[0]
input.type.imageType.colorSpace = ft.ImageFeatureType.RGB
input.type.imageType.height = 224
input.type.imageType.width = 224
coremltools.utils.save_spec(spec, "newModel.mlmodel")
My problem now is with the output type. I want to be able to access the confidence of the classification as well as the result label of the classification. Again using coremltools I was able to to access the output description and I got this.
name: "scores"
type {
	multiArrayType {
		dataType: FLOAT32
	}
}
I am trying to change it this way:
f = open("dict.txt", "r")
labels = f.read()
class_labels = labels.splitlines()
print(class_labels)
class_labels = class_labels[1:]
assert len(class_labels) == 57
for i, label in enumerate(class_labels):
	if isinstance(label, bytes):
		class_labels[i] = label.decode("utf8")
classifier_config = ct.ClassifierConfig(class_labels)
output = spec.description.output[0]
output.type = ft.DictionaryFeatureType
Unfortunately this is not working and I can't find information only that can help me... This I don't know what to do next.
Thank you for your help!
Selecting any option will automatically load the page
Post
Replies
Boosts
Views
Activity
Hello everybody,
I used Google Cloud Platform to create a Machine learning model to perform computer vision. I downloaded the CoreML model from the cloud platform website and followed the instructions in the Google Tutorial for iOS model deployment.
This is my code currently.
class Classification {
private lazy var classificationRequest: VNCoreMLRequest = {
do {
let model = try VNCoreMLModel(for: AutoML().model)
let request = VNCoreMLRequest(model: model, completionHandler: { [weak self] request, error in
if let classifications = request.results as? [VNClassificationObservation] {
print(classifications.first ?? "No classification!")
}
})
request.imageCropAndScaleOption = .scaleFit
return request
}
catch {
fatalError("Error! Can't use Model.")
}
}()
func classifyImage(receivedImage: UIImage) {
let orientation = CGImagePropertyOrientation(rawValue: UInt32(receivedImage.imageOrientation.rawValue))
if let image = CIImage(image: receivedImage) {
DispatchQueue.global(qos: .userInitiated).async {
let handler = VNImageRequestHandler(ciImage: image, orientation: orientation!)
do {
try handler.perform([self.classificationRequest])
}
catch {
fatalError("Error classifying image!")
}
}
}
}
My code executes and I receive this:
<VNClassificationObservation: 0x600002091d40> A7DBD70C-541C-4112-84A4-C6B4ED2EB7E2 requestRevision=1 confidence=0.332127 "CICAgICAwPmveRIJQWdsYWlzX2lv"
I receive a confidence value but I don't receive a label string.
Is there any step I am not taking?
With the model there is also a dict.txt file. Is there anything I have to do with that and that I am not doing?
Thank you!
Hello everybody,
I am building a Map and I am using a map view that I want to be always present in the interface. However, the user can share to show its location or not.
The Map view requires a region. But I want to show an empty map view with just the grid on with a message.
Do you know if it is possible to achieve that? Thank you!
let span = MKCoordinateSpan(latitudeDelta: CLLOcationDegrees, longitudeDelta: CLLOcationDegrees)
let region = MKCoordinateRegion(center: observationCoordinates, span: span)
				
let annotation =	MKPointAnnotation()
annotation.coordinate = observationCoordinates
				
uiView.setRegion(region, animated: true)
uiView.addAnnotation(annotation)
Hello everybody,
I am trying to navigate from one view to another using NavigationView and NavigationLink.
I can't figure out what I am doing wrong, but the way I am doing it I get a warning saying:
"Result of NavigationLink<Label, Destination> is unused".
In fact, I can't navigate to the view I want to open.
Here is my code so far:
NavigationView {
VStack {
Button(action: {
let observation = self.createObservation()
self.records.addObservation(observation)
self.isPresented.toggle()
NavigationLink(destination: ObservationDetails(observation: observation).environmentObject(self.records)) {
EmptyView()
}
}) {
Text("Classify")
}
}
Thank you for your help!
Hello everyone,
I want to use a map view to display an annotation but when I place it on the view it always stays in at the center of the map view.
I want to give it some offset so that it goes a little bit upwards.
This is the code I have so far. Could you please help me?
let span = MKCoordinateSpan(latitudeDelta: CLLOcationDegrees, longitudeDelta: CLLOcationDegrees)
let region = MKCoordinateRegion(center: observationCoordinates, span: span)
let annotation = MKPointAnnotation()
annotation.coordinate = observationCoordinates
uiView.setRegion(region, animated: true)
uiView.addAnnotation(annotation)
Thank you for your help.
Hello everybody,I am new to iOS development and I found an error that I can not get past. I have read a lot online and on Stackoverflow but I don't understand why this error keeps coming up.I have a table view controller and I want to write text to other view controller using:navigationController?.pushViewController(viewController, animated: true)I have this class where I already have an outlet for the label.import UIKit
class PetitionDetailsViewController: UIViewController {
@IBOutlet weak var PetitionDetailsOutlet: UILabel!
override func viewDidLoad() {
super.viewDidLoad()
}
}On the other class I have this code where I try to add text to the label in the PetitionDetailsViewController after tapping one of the rows in the table view.override func tableView(_ tableView: UITableView, didSelectRowAt indexPath: IndexPath) {
let viewController = PetitionDetailsViewController()
print(petitions[indexPath.row].body)
viewController.PetitionDetailsOutlet.text = petitions[indexPath.row].body
navigationController?.pushViewController(viewController, animated: true)
}I don't understand why this error keeps coming up. I have the outlet and initially the label is empty.Why is it nil?
Hello everybody ,Two days ago I submitted my first iOS app. I was super excited. Yesterday my app came back rejected with “metadata rejected”. I am very inexperienced and I kind of panic and tried everything to solve it. I replied in the resolution center and then I made the mistake of clicking submit for review. And now I am waiting.Sorry to bother you but I really would like to hear from somebody with experience what is going to happen now...- Since I clicked submit for review will my app be again in the beginning of the queue?- what happens to my response in the resolution center? Will my reviewer still read it?- How long, in the worst case scenario will it take to get some feedback back?Thank you so much.Best regards,