Swift
En innebygd kameraapp for Mac med Core ML-detektoren din.
Core ML · macOSBadBob / Playground
Gjør en trent modell til noe du kan bruke. Små eksempler med åpen kildekode, tydelige steg og kode du kan gjøre til din egen.
Åpen kildekode · MIT · Modellen din forblir din

01 / VELG DIN VEI
En innebygd kameraapp for Mac med Core ML-detektoren din.
Core ML · macOSEt skriptspor for å undersøke modeller og bygge nyttige verktøy.
ONNX Runtime · OpenCVNettlesereksempler med en støttet ONNX-modell.
Web · ONNXEt innebygd spor med tydelige krav til modell og kjøremiljø.
OpenCV · ONNXPraktiske verktøy med et tydelig grensesnitt til modellkjøring.
GoCV · ONNXKamera og lokal inferens med OpenCV og en støttet ONNX-modell.
OpenCV · ONNXDeviconGo Gopher — Renee FrenchCC BY 3.0
02 / Swift Core ML + Vision
Et komplett Swift-eksempel: velg modellen, start kameraet og tegn de tilhørende prediksjonene. Følg stegene eller utforsk hele koden.
Eksemplene handler om gjenstander og dyr i avgrensede omgivelser. De dekker ikke personovervåking, identifisering eller atferdsanalyse.
Last ned kildekoden og kjør testene. Du trenger et kamera og en Core ML-objektdetektor som virker med Vision. Modellvekter følger ikke med.
swift testunzip badbob-playground-swift.zip
cd badbob-playground-swift
swift testLast inn modellen og opprett en Vision-forespørsel. Kontroller inndata før kameraet starter, og behold midlertidige kompileringer så lenge inferensen bruker dem.
VisionDetector.init(modelURL:)VisionDetector.predict(_:)Eksemplet krever en Core ML-objektdetektor som returnerer objektobservasjoner i Vision. Andre modelltyper og ONNX-filer trenger en annen adapter.
Vision gir normaliserte koordinater fra nedre venstre hjørne. Omregn dem til visningen, behold proporsjonene og speil bilde og bokser sammen.
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)
}
}
}Opptaket kjører på sin egen serielle eksekutor. Forsinkede bilder droppes, og bare det nyeste behandlede bildet venter på grensesnittet. Bilde og prediksjoner hører sammen.
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 gir normaliserte koordinater fra nedre venstre hjørne. Omregn dem til visningen, behold proporsjonene og speil bilde og bokser sammen.
OverlayGeometry.project(...)Se bildestørrelse, beskjæring, retning og koordinater som én avtale. Test kjente bokser før du stoler på markeringene.
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
)
}
}Bygg den lokale appen, velg detektoren og trykk Start camera. Juster konfidensgrensen og speilingen. Stopp opptaket når du er ferdig.
CameraController.start()CameraController.stop()./build-app.sh
open ".build/BadBob Playground.app"02.06 / Gode arbeidsmåter