Update app.py

app.py

@@ -12,7 +12,7 @@ import tempfile
 model = YOLO("best.pt")
 model.to('cuda' if torch.cuda.is_available() else 'cpu')
 
-# Resolve class index for cricket ball
+# Resolve ball class index
 ball_class_index = None
 for k, v in model.names.items():
     if v.lower() == "cricketball":
@@ -25,7 +25,7 @@ if ball_class_index is None:
 STUMPS_WIDTH = 0.2286
 BALL_DIAMETER = 0.073
 FRAME_RATE = 20
-SLOW_MOTION_FACTOR = 2  # Set to 1 for normal speed replay
+SLOW_MOTION_FACTOR = 1  # Normal speed; increase to slow down
 CONF_THRESHOLD = 0.2
 IMPACT_ZONE_Y = 0.85
 IMPACT_DELTA_Y = 50
@@ -48,7 +48,10 @@ def process_video(video_path):
             break
         frame_count += 1
         frames.append(frame.copy())
-        results = model.predict(frame, conf=CONF_THRESHOLD, imgsz=(frame_height, frame_width), iou=0.5, max_det=1)
+
+        # 🚀 Faster inference with fixed optimized size
+        results = model.predict(frame, conf=CONF_THRESHOLD, imgsz=640, iou=0.5, max_det=1)
+
         detections = 0
         for detection in results[0].boxes:
             if int(detection.cls) == ball_class_index:
@@ -58,10 +61,11 @@ def process_video(video_path):
                     ball_positions.append([(x1 + x2) / 2, (y1 + y2) / 2])
                     detection_frames.append(frame_count - 1)
                     cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
+
         frames[-1] = frame
         debug_log.append(f"Frame {frame_count}: {detections} ball detections")
-    cap.release()
 
+    cap.release()
     return frames, ball_positions, detection_frames, "\n".join(debug_log)
 
 def find_bounce_point(ball_coords):