Swift
A native Mac camera app with your Core ML detector.
Core ML · macOSBadBob / Playground
Turn a trained model into something you can use. Small open source examples, clear steps, and code you can make your own.
Open source · MIT · Your model stays yours

01 / CHOOSE YOUR PATH
A native Mac camera app with your Core ML detector.
Core ML · macOSA scripting path for inspecting models and building practical tools.
ONNX Runtime · OpenCVBrowser examples with a supported ONNX model.
Web · ONNXA native path with explicit model and runtime requirements.
OpenCV · ONNXPractical tools with a clear model-serving boundary.
GoCV · ONNXCamera and local inference with OpenCV and a supported ONNX model.
OpenCV · ONNXDeviconGo Gopher — Renee FrenchCC BY 3.0
02 / Swift Core ML + Vision
A complete Swift example: choose your model, start the camera, and draw the matching predictions. Read the parts in order or explore the full source.
These examples focus on objects and animals in controlled settings. They do not cover people surveillance, identification or behavioral analysis.
Download the source and run its tests. You need a camera and a Vision-compatible Core ML object detector. No model weights are included.
swift testunzip badbob-playground-swift.zip
cd badbob-playground-swift
swift testLoad your model and create a Vision request. Check its inputs before starting the camera, and keep any temporary compilation for the lifetime of inference.
VisionDetector.init(modelURL:)VisionDetector.predict(_:)This example requires a Core ML object detector that returns Vision object observations. Other model types and ONNX files need a different adapter.
Vision reports normalized coordinates from the bottom left. Convert them to your view, preserve the image aspect ratio, and mirror the image and boxes together.
model:
runtime: Core ML + Vision
formats: [.mlmodel, .mlpackage, .mlmodelc]
image_inputs: 1
results: VNRecognizedObjectObservation
preprocessing:
crop_and_scale: scaleFill
orientation: up
coordinates:
range: [0, 1]
origin: bottom_left
preview:
scaling: aspect_fit
mirroring: pairedimport CoreML
import Foundation
import Vision
/// Owned by one frame processor and used only on its serial capture queue.
final class VisionDetector {
private let request: VNCoreMLRequest
private let compiledURL: URL?
private let scopedURL: URL?
init(modelURL: URL) throws {
guard modelURL.isFileURL,
["mlmodel", "mlpackage", "mlmodelc"].contains(modelURL.pathExtension.lowercased())
else {
throw CaptureFailure.unsupportedModel
}
let scoped = modelURL.startAccessingSecurityScopedResource()
var ownedCompilation: URL?
do {
let loadURL: URL
if modelURL.pathExtension.lowercased() == "mlmodelc" {
loadURL = modelURL
} else {
loadURL = try MLModel.compileModel(at: modelURL)
ownedCompilation = loadURL
}
let model = try MLModel(contentsOf: loadURL)
guard
model.modelDescription.inputDescriptionsByName.values.filter({ $0.type == .image })
.count == 1
else {
throw CaptureFailure.unsupportedModel
}
request = VNCoreMLRequest(model: try VNCoreMLModel(for: model))
request.imageCropAndScaleOption = .scaleFill
compiledURL = ownedCompilation
scopedURL = scoped ? modelURL : nil
} catch {
if scoped {
modelURL.stopAccessingSecurityScopedResource()
}
if let ownedCompilation {
try? FileManager.default.removeItem(at: ownedCompilation)
}
throw error
}
}
deinit {
// Predictions have ended; remove only our own temporary compilation.
if let compiledURL {
try? FileManager.default.removeItem(at: compiledURL)
}
scopedURL?.stopAccessingSecurityScopedResource()
}
func predict(_ buffer: CVPixelBuffer) throws -> [Detection] {
try VNImageRequestHandler(cvPixelBuffer: buffer, orientation: .up).perform([request])
guard let objects = request.results as? [VNRecognizedObjectObservation] else {
throw CaptureFailure.unsupportedModel
}
return objects.enumerated().compactMap { index, observation in
guard let label = observation.labels.first, label.confidence.isFinite else {
return nil
}
return Detection(
id: index, label: label.identifier, confidence: label.confidence,
bounds: observation.boundingBox)
}
}
}Capture runs on its own serial executor. Late frames are discarded, and only the newest processed frame waits for the interface. Pixels and predictions stay together.
CameraService.start(runID:modelURL:)CameraService.stop(runID:)import AVFoundation
import CoreImage
import Dispatch
import Foundation
/// A custom executor keeps blocking AVFoundation work off the main actor.
public actor CameraService: CameraCapturing {
private nonisolated let queue = DispatchSerialQueue(label: "ai.badbob.playground.camera")
public nonisolated var unownedExecutor: UnownedSerialExecutor {
queue.asUnownedSerialExecutor()
}
private var session: AVCaptureSession?
private var output: AVCaptureVideoDataOutput?
private var processor: FrameProcessor?
private var monitor: CaptureSessionMonitor?
private var activeRunID: UUID?
public init() {}
public func start(runID: UUID, modelURL: URL) async throws -> FrameStream {
stopActiveRun()
let detector = try loadDetector(modelURL: modelURL)
try Task.checkCancellation()
guard let camera = AVCaptureDevice.default(for: .video) else {
throw CaptureFailure.noCamera
}
let candidate = AVCaptureSession()
let frames = AVCaptureVideoDataOutput()
let (stream, continuation) = FrameStream.makeStream(bufferingPolicy: .bufferingNewest(1))
let delegate = FrameProcessor(detector: detector, continuation: continuation)
try configureSession(candidate, output: frames, processor: delegate, camera: camera)
try Task.checkCancellation()
session = candidate
output = frames
processor = delegate
activeRunID = runID
monitor = CaptureSessionMonitor(session: candidate, continuation: continuation)
continuation.onTermination = { [weak self] _ in
Task { await self?.stop(runID: runID) }
}
candidate.startRunning()
guard candidate.isRunning else {
stopActiveRun()
throw CaptureFailure.configuration
}
return stream
}
private func loadDetector(modelURL: URL) throws -> VisionDetector {
do {
return try VisionDetector(modelURL: modelURL)
} catch let error as CaptureFailure {
throw error
} catch {
throw CaptureFailure.model(error.localizedDescription)
}
}
private func configureSession(
_ candidate: AVCaptureSession,
output frames: AVCaptureVideoDataOutput,
processor delegate: FrameProcessor,
camera: AVCaptureDevice
) throws {
candidate.beginConfiguration()
do {
let input = try AVCaptureDeviceInput(device: camera)
guard candidate.canAddInput(input), candidate.canAddOutput(frames) else {
throw CaptureFailure.configuration
}
candidate.addInput(input)
candidate.addOutput(frames)
if candidate.canSetSessionPreset(.hd1280x720) {
candidate.sessionPreset = .hd1280x720
}
frames.alwaysDiscardsLateVideoFrames = true
frames.videoSettings = [
kCVPixelBufferPixelFormatTypeKey as String: kCVPixelFormatType_32BGRA
]
// The delegate, Vision request and frame renderer share this one serial queue.
frames.setSampleBufferDelegate(delegate, queue: queue)
if let connection = frames.connection(with: .video),
connection.isVideoMirroringSupported
{
connection.automaticallyAdjustsVideoMirroring = false
connection.isVideoMirrored = false
}
candidate.commitConfiguration()
} catch {
candidate.commitConfiguration()
frames.setSampleBufferDelegate(nil, queue: nil)
delegate.finish()
throw error
}
}
public func stop(runID: UUID) {
// A cancelled old task must not stop a more recent capture run.
guard activeRunID == runID else {
return
}
stopActiveRun()
}
private func stopActiveRun() {
// Remove observers first so our deliberate stop cannot become a failure.
monitor?.invalidate()
monitor = nil
session?.stopRunning()
output?.setSampleBufferDelegate(nil, queue: nil)
processor?.finish()
processor = nil
output = nil
session = nil
activeRunID = nil
}
}
/// AVFoundation invokes this delegate only on CameraService's serial queue.
/// No sample buffer or mutable Vision object crosses into a Task or the UI.
private final class FrameProcessor: NSObject, AVCaptureVideoDataOutputSampleBufferDelegate {
private let detector: VisionDetector
private let continuation: FrameStream.Continuation
private let renderer = CIContext(options: [.cacheIntermediates: false])
private var finished = false
init(detector: VisionDetector, continuation: FrameStream.Continuation) {
self.detector = detector
self.continuation = continuation
}
func finish() {
guard !finished else {
return
}
finished = true
continuation.finish()
}
func captureOutput(
_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer,
from connection: AVCaptureConnection
) {
guard !finished, let buffer = CMSampleBufferGetImageBuffer(sampleBuffer) else {
return
}
autoreleasepool {
do {
let detections = try detector.predict(buffer)
let image = CIImage(cvPixelBuffer: buffer)
guard let pixels = renderer.createCGImage(image, from: image.extent) else {
throw CaptureFailure.imageCreation
}
continuation.yield(DetectionFrame(image: pixels, detections: detections))
} catch {
finished = true
continuation.finish(throwing: error)
}
}
}
}Vision reports normalized coordinates from the bottom left. Convert them to your view, preserve the image aspect ratio, and mirror the image and boxes together.
OverlayGeometry.project(...)Treat image size, crop, orientation and coordinates as one contract. Test it with known boxes before trusting an overlay.
import CoreGraphics
/// Convert Vision's normalized, bottom-left coordinates to an aspect-fit view.
public enum OverlayGeometry {
public static func project(
_ bounds: CGRect, imageSize: CGSize, viewport: CGSize, mirrored: Bool
) -> CGRect? {
guard
[imageSize.width, imageSize.height, viewport.width, viewport.height].allSatisfy({
$0.isFinite && $0 > 0
}),
[bounds.origin.x, bounds.origin.y, bounds.width, bounds.height].allSatisfy(\.isFinite),
bounds.width > 0, bounds.height > 0
else { return nil }
let clipped = bounds.intersection(CGRect(x: 0, y: 0, width: 1, height: 1))
guard !clipped.isNull, !clipped.isEmpty else {
return nil
}
let scale = min(viewport.width / imageSize.width, viewport.height / imageSize.height)
let width = imageSize.width * scale
let height = imageSize.height * scale
return CGRect(
x: (viewport.width - width) / 2 + (mirrored ? 1 - clipped.maxX : clipped.minX) * width,
y: (viewport.height - height) / 2 + (1 - clipped.maxY) * height,
width: clipped.width * width, height: clipped.height * height
)
}
}Build the local app, choose your detector, and press Start camera. Adjust the confidence threshold and mirror control. Stop capture when you are done.
CameraController.start()CameraController.stop()./build-app.sh
open ".build/BadBob Playground.app"02.06 / Best practices