Inferencing perfomance

app/page.tsx

@@ -19,10 +19,8 @@ type CameraStatus = 'loading' | 'active' | 'denied' | 'no_devices';
 
 export default function HomePage() {
   const videoRef = useRef<HTMLVideoElement>(null);
-  const canvasRef = useRef<HTMLCanvasElement>(null);
   const [stream, setStream] = useState<MediaStream | null>(null);
   const [cameraStatus, setCameraStatus] = useState<CameraStatus>('loading');
-  const [canvasCtx, setCanvasCtx] = useState<CanvasRenderingContext2D | null>(null);
 
   const [videoDevices, setVideoDevices] = useState<MediaDeviceInfo[]>([]);
   const [selectedDeviceId, setSelectedDeviceId] = useState<string>('');
@@ -40,80 +38,11 @@ export default function HomePage() {
   const [shoeDetectionCount, setShoeDetectionCount] = useState(0);
   const [lastSoundTime, setLastSoundTime] = useState(0);
 
-  // Draw detections function - defined early to avoid initialization order issues
-  const drawDetections = useCallback((
-    detection: DetectionResult | null,
-    ctx: CanvasRenderingContext2D,
-    video: HTMLVideoElement,
-    canvas: HTMLCanvasElement
-  ) => {
-    console.log('🎨 drawDetections called:', { detection, videoSize: { width: video.videoWidth, height: video.videoHeight }, canvasSize: { width: canvas.width, height: canvas.height } });
-    
-    // Clear canvas
-    ctx.clearRect(0, 0, canvas.width, canvas.height);
-    
-    if (!detection) {
-      console.log('❌ No detection to draw');
-      return;
-    }
 
-    const videoWidth = video.videoWidth;
-    const videoHeight = video.videoHeight;
-    
-    // Ensure canvas matches video dimensions
-    if (canvas.width !== videoWidth || canvas.height !== videoHeight) {
-      canvas.width = videoWidth;
-      canvas.height = videoHeight;
-    }
-    
-    // Get bounding box coordinates [x, y, width, height]
-    const [x, y, width, height] = detection.bbox;
-    
-    // Convert normalized coordinates to pixel coordinates
-    const displayX = x * videoWidth;
-    const displayY = y * videoHeight;
-    const displayWidth = width * videoWidth;
-    const displayHeight = height * videoHeight;
-    
-    // Draw bounding box with glow effect
-    ctx.shadowColor = '#ff0000';
-    ctx.shadowBlur = 10;
-    ctx.strokeStyle = '#ff0000';
-    ctx.lineWidth = 3;
-    ctx.strokeRect(displayX, displayY, displayWidth, displayHeight);
-    
-    // Reset shadow for text
-    ctx.shadowBlur = 0;
-    
-    // Draw label with background
-    const labelText = `${detection.class} (${(detection.confidence * 100).toFixed(1)}%)`;
-    ctx.font = 'bold 16px Arial';
-    const textMetrics = ctx.measureText(labelText);
-    const textWidth = textMetrics.width;
-    const textHeight = 16;
-    const padding = 6;
-    
-    // Label background
-    ctx.fillStyle = 'rgba(255, 0, 0, 0.8)';
-    ctx.fillRect(
-      displayX, 
-      displayY > textHeight + padding ? displayY - textHeight - padding : displayY + displayHeight + 2,
-      textWidth + padding * 2,
-      textHeight + padding
-    );
-    
-    // Label text
-    ctx.fillStyle = 'white';
-    ctx.fillText(
-      labelText,
-      displayX + padding,
-      displayY > textHeight + padding ? displayY - padding : displayY + displayHeight + textHeight + padding
-    );
-  }, []);
-
-  // Stable detection callback using useCallback to prevent re-registration
+  // Clean detection callback - no canvas drawing needed
   const handleDetection = useCallback((detection: DetectionResult | null) => {
-    console.log('🔍 Detection callback received:', detection);
+    const callbackId = Math.random().toString(36).substr(2, 9);
+    console.log(`🔍 Detection callback received [${callbackId}]:`, detection);
     setCurrentDetection(detection);
     
     // Count actual shoe detections (not just inference attempts)
@@ -121,47 +50,49 @@ export default function HomePage() {
       setShoeDetectionCount(prev => prev + 1);
     }
     
-    // Get canvas context if not available
-    let ctx = canvasCtx;
-    if (canvasRef.current && !ctx) {
-      ctx = canvasRef.current.getContext('2d');
-      if (ctx) {
-        setCanvasCtx(ctx);
-      }
-    }
-    
-    // Draw detection if we have everything we need
-    if (ctx && videoRef.current && canvasRef.current) {
-      console.log('🎨 Drawing detection on canvas');
-      drawDetections(detection, ctx, videoRef.current, canvasRef.current);
-    } else {
-      console.log('❌ Canvas drawing skipped - missing refs:', { canvasCtx: !!ctx, video: !!videoRef.current, canvas: !!canvasRef.current });
-    }
-    
     // Auto-trigger popup when shoe is detected with high confidence
     if (detection && detection.confidence > 0.7) {
-      console.log('🎯 HIGH CONFIDENCE SHOE DETECTED! Opening popup...', detection);
+      console.log(`🎯 HIGH CONFIDENCE SHOE DETECTED! [${callbackId}] Opening popup...`, detection);
       setPopupOpen(true);
       
       // Play detection sound with debouncing (max once per 2 seconds)
       setLastSoundTime(currentTime => {
         const now = Date.now();
+        console.log(`🔊 Sound check [${callbackId}]: now=${now}, lastTime=${currentTime}, diff=${now - currentTime}ms`);
+        
         if (now - currentTime > 2000) {
           try {
-            const audio = new Audio('data:audio/wav;base64,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');
-            console.log('🔊 Playing detection sound');
-            audio.play();
+            const audioId = Math.random().toString(36).substr(2, 9);
+            // Use AudioContext for more reliable single-play behavior
+            const audioContext = new (window.AudioContext || (window as any).webkitAudioContext)();
+            console.log(`🔊 Playing detection sound [callback:${callbackId}] [audio:${audioId}]`);
+            
+            // Simple beep using Web Audio API
+            const oscillator = audioContext.createOscillator();
+            const gainNode = audioContext.createGain();
+            
+            oscillator.connect(gainNode);
+            gainNode.connect(audioContext.destination);
+            
+            oscillator.frequency.setValueAtTime(800, audioContext.currentTime);
+            gainNode.gain.setValueAtTime(0.3, audioContext.currentTime);
+            gainNode.gain.exponentialRampToValueAtTime(0.001, audioContext.currentTime + 0.3);
+            
+            oscillator.start(audioContext.currentTime);
+            oscillator.stop(audioContext.currentTime + 0.3);
+            
+            console.log(`▶️ Audio beep started [${audioId}]`);
           } catch (e) {
-            console.warn('Sound playback failed:', e);
+            console.warn(`Sound playback failed [${callbackId}]:`, e);
           }
           return now;
         } else {
-          console.log('🔇 Sound skipped - too soon after last sound');
+          console.log(`🔇 Sound skipped [${callbackId}] - too soon after last sound (${now - currentTime}ms ago)`);
           return currentTime;
         }
       });
     }
-  }, [canvasCtx, drawDetections]);
+  }, []);
 
   // Initialize ML detection system
   const {
@@ -199,49 +130,30 @@ export default function HomePage() {
     }
   }, [stream, cameraStatus]); // Runs when stream or camera status changes
 
-  // Effect to get canvas context - ensure it's available
-  useEffect(() => {
-    if (canvasRef.current && !canvasCtx) {
-      const ctx = canvasRef.current.getContext('2d');
-      if (ctx) {
-        console.log('📝 Canvas context initialized');
-        setCanvasCtx(ctx);
-      }
-    }
-  }, [canvasRef, canvasCtx]);
 
   // Track initialization state to prevent multiple attempts
   const [mlInitialized, setMLInitialized] = useState(false);
 
   // Initialize ML detection when camera is ready (only once)
   useEffect(() => {
-    console.log('🔍 ML initialization useEffect triggered:', {
-      hasVideo: !!videoRef.current,
-      cameraStatus,
-      isMLLoading,
-      detectionEnabled,
-      mlInitialized
-    });
+    // Only log in development and when conditions change meaningfully
+    if (process.env.NODE_ENV === 'development') {
+      console.log('🔍 ML init check:', { 
+        ready: videoRef.current && cameraStatus === 'active' && !isMLLoading && detectionEnabled && !mlInitialized 
+      });
+    }
     
     if (videoRef.current && cameraStatus === 'active' && !isMLLoading && detectionEnabled && !mlInitialized) {
-      console.log('✅ All conditions met, initializing ML detection...');
+      console.log('✅ Starting ML detection...');
       setMLInitialized(true);
       
       initializeML(videoRef.current).then(() => {
-        console.log('✅ ML detection initialized, starting continuous detection');
+        console.log('✅ ML ready, starting continuous detection');
         startContinuous();
       }).catch((error) => {
-        console.error('❌ Failed to initialize ML detection:', error);
+        console.error('❌ ML initialization failed:', error);
         setMLInitialized(false); // Reset on error to allow retry
       });
-    } else {
-      console.log('⏳ Waiting for conditions:', {
-        hasVideo: !!videoRef.current,
-        cameraActive: cameraStatus === 'active',
-        notLoading: !isMLLoading,
-        detectionEnabled,
-        alreadyInitialized: mlInitialized
-      });
     }
   }, [cameraStatus, detectionEnabled, isMLLoading, mlInitialized, initializeML, startContinuous]);
 
@@ -461,7 +373,6 @@ export default function HomePage() {
         return (
           <>
             <video ref={videoRef} autoPlay playsInline muted onCanPlay={() => videoRef.current?.play()} className="h-full w-full object-cover" />
-            <canvas ref={canvasRef} className="absolute top-0 left-0 w-full h-full"></canvas>
             
             {/* ML Detection Status Indicator */}
             {detectionEnabled && (

lib/ml/detection-engine.ts

@@ -165,7 +165,10 @@ export class DetectionEngine {
     }
     
     this.frameSkipCounter = 0;
-    console.log('🔄 Running continuous detection frame...');
+    // Only log every 10th detection to reduce noise
+    if (this.metrics.detectionCount % 10 === 0) {
+      console.log(`🔄 Continuous detection running... (${this.metrics.detectionCount} inferences)`);
+    }
     
     try {
       const startTime = performance.now();

workers/detection-worker.ts

@@ -119,17 +119,9 @@ async function detect(imageData: ImageData, id: string) {
     );
     tensor.dispose();
 
-    console.log('Worker: Model execution result:', result);
-    console.log('Worker: Result type:', typeof result);
-    console.log('Worker: Result is array:', Array.isArray(result));
-    
-    if (result) {
-      console.log('Worker: Result length:', result.length);
-      if (Array.isArray(result)) {
-        result.forEach((item, index) => {
-          console.log(`Worker: Result[${index}]:`, item, 'shape:', item?.shape);
-        });
-      }
+    // Reduced logging for performance
+    if (process.env.NODE_ENV === 'development') {
+      console.log('Worker: Model execution completed, processing results...');
     }
 
     if (!result || !Array.isArray(result) || result.length < 4) {
@@ -146,20 +138,13 @@ async function detect(imageData: ImageData, id: string) {
     const scoresData = await scores.data();
     const classesData = await classes.data();
     
-    console.log('Worker: Raw model outputs:', {
-      boxesShape: boxes.shape,
-      scoresShape: scores.shape,
-      classesShape: classes.shape,
-      boxesLength: boxesData.length,
-      scoresLength: scoresData.length,
-      classesLength: classesData.length,
-      firstFewBoxes: Array.from(boxesData.slice(0, 8)),
-      firstFewScores: Array.from(scoresData.slice(0, 4)),
-      firstFewClasses: Array.from(classesData.slice(0, 4)),
-      maxScore: Math.max(...Array.from(scoresData.slice(0, 10))),
-      scoresAbove20: Array.from(scoresData.slice(0, 10)).filter(s => s > 0.2).length,
-      scoresAbove30: Array.from(scoresData.slice(0, 10)).filter(s => s > 0.3).length
-    });
+    // Only log detailed outputs when debugging specific issues
+    const maxScore = Math.max(...Array.from(scoresData.slice(0, 10)));
+    const scoresAbove30 = Array.from(scoresData.slice(0, 10)).filter(s => s > 0.3).length;
+    
+    if (process.env.NODE_ENV === 'development' && (maxScore > 0.3 || scoresAbove30 > 0)) {
+      console.log('Worker: Potential detection found:', { maxScore, scoresAbove30 });
+    }
 
     result.forEach(t => t.dispose());