MobileNetV2 サンプルコードを解読

概要

数回に渡って、CoreModelの学習モデルのiOSでの使い方について、サンプルコードのCoreMLに関わる部分を中心に解読していく。

・参考URL
https://developer.apple.com/jp/machine-learning/models/#text

今回はMobileNetV2を解読する。

MobileNetV2

MLModelセットアップ

// MARK: - Image Classification

    /// - Tag: MLModelSetup
    lazy var classificationRequest: VNCoreMLRequest = {
        do {
            /*
             Use the Swift class `MobileNet` Core ML generates from the model.
             To use a different Core ML classifier model, add it to the project
             and replace `MobileNet` with that model's generated Swift class.
             */
            let model = try VNCoreMLModel(for: MobileNet().model)

            let request = VNCoreMLRequest(model: model, completionHandler: { [weak self] request, error in
                self?.processClassifications(for: request, error: error)
            })
            request.imageCropAndScaleOption = .centerCrop
            return request
        } catch {
            fatalError("Failed to load Vision ML model: \(error)")
        }
    }()

一箇所ずつ何をやっているか解読。

// MobileNet modelからMobileNetクラスを生成し、そのクラスからインスタンスを生成
let model = try VNCoreMLModel(for: MobileNet().model)

// VNCoreMLRequestオブジェクトを生成、
// リクエスト後、モデルから結果を受け取るメソッドを指定するためにcompletionHandlerを使用。 
let request = VNCoreMLRequest(model: model, completionHandler: { [weak self] request, error in
                self?.processClassifications(for: request, error: error)
            })

// 画像のスケール方法を決定
request.imageCropAndScaleOption = .centerCrop

リクエスト実行

/// - Tag: PerformRequests
    func updateClassifications(for image: UIImage) {
        classificationLabel.text = "Classifying..."

        let orientation = CGImagePropertyOrientation(image.imageOrientation)
        guard let ciImage = CIImage(image: image) else { fatalError("Unable to create \(CIImage.self) from \(image).") }

        DispatchQueue.global(qos: .userInitiated).async {
            let handler = VNImageRequestHandler(ciImage: ciImage, orientation: orientation)
            do {
                try handler.perform([self.classificationRequest])
            } catch {
                /*
                 This handler catches general image processing errors. The `classificationRequest`'s
                 completion handler `processClassifications(_:error:)` catches errors specific
                 to processing that request.
                 */
                print("Failed to perform classification.\n\(error.localizedDescription)")
            }
        }
    }

// 画像の向きを取得
// imageからCIImageに変換
let orientation = CGImagePropertyOrientation(image.imageOrientation)
        guard let ciImage = CIImage(image: image) else { fatalError("Unable to create \(CIImage.self) from \(image).") }

DispatchQueue.global(qos: .userInitiated).async {
            let handler = VNImageRequestHandler(ciImage: ciImage, orientation: orientation)
            do {
                try handler.perform([self.classificationRequest])
            } catch {
                /*
                 This handler catches general image processing errors. The `classificationRequest`'s
                 completion handler `processClassifications(_:error:)` catches errors specific
                 to processing that request.
                 */
                print("Failed to perform classification.\n\(error.localizedDescription)")
            }
        }

プロセス分類

/// Updates the UI with the results of the classification.
    /// - Tag: ProcessClassifications
    func processClassifications(for request: VNRequest, error: Error?) {
        DispatchQueue.main.async {
            guard let results = request.results else {
                self.classificationLabel.text = "Unable to classify image.\n\(error!.localizedDescription)"
                return
            }
            // The `results` will always be `VNClassificationObservation`s, as specified by the Core ML model in this project.
            let classifications = results as! [VNClassificationObservation]

            if classifications.isEmpty {
                self.classificationLabel.text = "Nothing recognized."
            } else {
                // Display top classifications ranked by confidence in the UI.
                let topClassifications = classifications.prefix(2)
                let descriptions = topClassifications.map { classification in
                    // Formats the classification for display; e.g. "(0.37) cliff, drop, drop-off".
                   return String(format: "  (%.2f) %@", classification.confidence, classification.identifier)
                }
                self.classificationLabel.text = "Classification:\n" + descriptions.joined(separator: "\n")
            }
        }
    }

上記は、分類結果をラベルに表示している。