Update app.py

app.py

@@ -17,20 +17,30 @@ model = YOLO("/home/user/app/best.pt")  # আপনি যেই path এ best.p
     
 # Frame processing function
 def process_frame(frame):
-    img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    # Resize image to 640x640
+    frame_resized = cv2.resize(frame, (640, 640))
+    
+    img = cv2.cvtColor(frame_resized, cv2.COLOR_BGR2RGB)
     img_tensor = torch.from_numpy(img).permute(2, 0, 1).float() / 255.0
     img_tensor = img_tensor.unsqueeze(0)
 
+    # Run inference with the YOLO model (no need to manually apply nms)
     results = model(img_tensor, augment=False)
-    results = model.nms(results)[0]
+    
+    # Extract results (list of detections)
+    detections = results.xywh[0]  # YOLO's detection results
 
     extracted_texts = []
     confidences = []
 
-    for det in results:
-        x1, y1, x2, y2, conf, cls = det.tolist()
+    for det in detections:
+        x_center, y_center, width, height, conf, cls = det.tolist()
         if conf > 0.5:
-            x1, y1, x2, y2 = map(int, (x1, y1, x2, y2))
+            # Convert from YOLO format to bounding box format
+            x1 = int((x_center - width / 2) * 640)
+            y1 = int((y_center - height / 2) * 640)
+            x2 = int((x_center + width / 2) * 640)
+            y2 = int((y_center + height / 2) * 640)
             cls = int(cls)
 
             label_map = {0: "Analog", 1: "Digital", 2: "Non-LP"}
@@ -51,6 +61,7 @@ def process_frame(frame):
 
     return frame, "\n".join(extracted_texts), ", ".join(confidences)
 
+
 # Input handler
 def process_input(input_file):
     file_path = input_file.name