オンデバイス画像認識、React Native の TFLite か Rork Max の Core ML か — 同じ題材で両方組んで決めた選び方

// ImageClassifier.swift
import CoreML
import Vision
 
final class ImageClassifier {
    private let request: VNCoreMLRequest
 
    init(model: MLModel) throws {
        let vnModel = try VNCoreMLModel(for: model)
        request = VNCoreMLRequest(model: vnModel)
        // リサイズと正規化を Vision に任せます。自前で書かない、が要点です
        request.imageCropAndScaleOption = .centerCrop
    }
 
    /// CGImage をそのまま渡します。Base64 も中間ファイルも経由しません
    func classify(_ cgImage: CGImage) throws -> [(String, Float)] {
        let handler = VNImageRequestHandler(cgImage: cgImage, options: [:])
        try handler.perform([request])
 
        guard let results = request.results as? [VNClassificationObservation] else {
            return []
        }
        return results.prefix(5).map { ($0.identifier, $0.confidence) }
    }
}

// utils/latencyProbe.ts
type Stage = 'capture' | 'read' | 'decode' | 'preprocess' | 'infer' | 'postprocess';
 
export class LatencyProbe {
  private marks: Array<[Stage, number]> = [];
  private t0 = 0;
 
  start() {
    this.marks = [];
    this.t0 = performance.now();
  }
 
  /// 各段の「終わった時刻」を積むだけ。差分は後で取ります
  mark(stage: Stage) {
    this.marks.push([stage, performance.now()]);
  }
 
  /// 段ごとの所要 ms と合計を返します
  report(): { breakdown: Record<string, number>; totalMs: number } {
    const breakdown: Record<string, number> = {};
    let prev = this.t0;
 
    for (const [stage, at] of this.marks) {
      breakdown[stage] = Math.round((at - prev) * 10) / 10;
      prev = at;
    }
    return { breakdown, totalMs: Math.round((prev - this.t0) * 10) / 10 };
  }
}

const probe = new LatencyProbe();
probe.start();
 
const photo = await cameraRef.current.takePictureAsync({ quality: 0.5, skipProcessing: true });
probe.mark('capture');
 
const b64 = await FileSystem.readAsStringAsync(photo.uri, { encoding: FileSystem.EncodingType.Base64 });
probe.mark('read');
 
const image = decodeJpeg(new Uint8Array(tf.util.encodeString(b64, 'base64').buffer));
probe.mark('decode');
 
const input = tf.tidy(() => tf.image.resizeBilinear(image, [224, 224]).div(127.5).sub(1).expandDims(0));
probe.mark('preprocess');
 
const logits = model.predict(input) as tf.Tensor;
const probs = await logits.data();
probe.mark('infer');
 
const top5 = toTop5(probs);
probe.mark('postprocess');
 
console.log(probe.report());
// 出力例: { breakdown: { capture: 118.4, read: 96.2, decode: 141.7, preprocess: 28.9, infer: 19.6, postprocess: 3.1 }, totalMs: 407.9 }

import os
 
let log = OSLog(subsystem: "net.rorklab.classifier", category: .pointsOfInterest)
 
os_signpost(.begin, log: log, name: "decode")
let cgImage = try decodeImage(from: data)
os_signpost(.end, log: log, name: "decode")
 
os_signpost(.begin, log: log, name: "infer")
let results = try classifier.classify(cgImage)
os_signpost(.end, log: log, name: "infer")