Update app.py

app.py

@@ -17,8 +17,8 @@ workspace = os.getenv("ROBOFLOW_WORKSPACE")
 project_name = os.getenv("ROBOFLOW_PROJECT")
 model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
 
-# CountGD Config (menggantikan DINO-X)
-# Pastikan API key CountGD telah di-set di .env dengan key COUNTGD_API_KEY
+# CountGD Config (Replace DINO-X)
+# Pastikan Anda sudah set COUNTGD_API_KEY di .env
 COUNTGD_API_KEY = os.getenv("COUNTGD_API_KEY")
 
 # Inisialisasi YOLO Model dari Roboflow
@@ -26,14 +26,11 @@ rf = Roboflow(api_key=rf_api_key)
 project = rf.workspace(workspace).project(project_name)
 yolo_model = project.version(model_version).model
 
-# List prompt untuk CountGD (misal: cans, bottle, mixed box)
-COUNTGD_PROMPTS = ["cans", "bottle", "mixed box"]
-
 # ========== Fungsi untuk Mengecek Overlap ==========
 def is_overlap(box1, boxes2, threshold=0.3):
     """
     Mengecek apakah box1 (format: (x_min, y_min, x_max, y_max)) overlap dengan salah satu box di boxes2.
-    boxes2 adalah list bounding box dari YOLO dengan format (x_center, y_center, width, height).
+    boxes2 adalah list bounding box YOLO dengan format (x_center, y_center, width, height).
     Mengembalikan True jika rasio overlap melebihi threshold.
     """
     x1_min, y1_min, x1_max, y1_max = box1
@@ -55,58 +52,65 @@ def is_overlap(box1, boxes2, threshold=0.3):
 
 # ========== Fungsi Deteksi Kombinasi ==========
 def detect_combined(image):
+    # Simpan image ke file sementara
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
         image.save(temp_file, format="JPEG")
         temp_path = temp_file.name
-    
+
     try:
         # ===== YOLO Detection (Produk Nestlé) =====
         yolo_pred = yolo_model.predict(temp_path, confidence=50, overlap=80).json()
         nestle_class_count = {}
-        nestle_boxes = []  # Menyimpan bounding box YOLO dengan format (x_center, y_center, width, height)
+        nestle_boxes = []  # Menyimpan bounding box YOLO (format: x_center, y_center, width, height)
         for pred in yolo_pred['predictions']:
             class_name = pred['class']
             nestle_class_count[class_name] = nestle_class_count.get(class_name, 0) + 1
             nestle_boxes.append((pred['x'], pred['y'], pred['width'], pred['height']))
         total_nestle = sum(nestle_class_count.values())
-        
+
         # ===== CountGD Detection (Produk Kompetitor) =====
         url = "https://api.landing.ai/v1/tools/text-to-object-detection"
-        files = {"image": open(temp_path, "rb")}
-        # Menggunakan lebih dari satu prompt
-        data = {"prompts": COUNTGD_PROMPTS, "model": "countgd"}
+        competitor_class_count = {}
+        competitor_boxes = []  # Menyimpan bounding box CountGD (format: x_min, y_min, x_max, y_max)
+        # Daftar prompt yang akan digunakan
+        COUNTGD_PROMPTS = ["cans", "bottle", "mixed box"]
         headers = {"Authorization": f"Basic {COUNTGD_API_KEY}"}
-        response = requests.post(url, files=files, data=data, headers=headers)
-        result = response.json()
         
-        competitor_class_count = {}
-        competitor_boxes = []  # Menyimpan bounding box CountGD dengan format (x_min, y_min, x_max, y_max)
-        if 'data' in result:
-            # Asumsi API mengembalikan list deteksi pada data[0]
-            for obj in result['data'][0]:
-                if 'bounding_box' in obj:
-                    x1, y1, x2, y2 = obj['bounding_box']
-                    # Mengambil label jika tersedia, default 'unclassified'
-                    label = obj.get('label', 'unclassified')
-                    # Hanya tambahkan deteksi jika tidak overlap dengan deteksi YOLO
-                    if not is_overlap((x1, y1, x2, y2), nestle_boxes, threshold=0.3):
-                        competitor_class_count[label] = competitor_class_count.get(label, 0) + 1
-                        competitor_boxes.append((x1, y1, x2, y2))
+        for prompt in COUNTGD_PROMPTS:
+            # Untuk setiap prompt, buka file gambar dan kirim request
+            with open(temp_path, "rb") as f:
+                files = {"image": f}
+                data = {"prompts": [prompt], "model": "countgd"}
+                response = requests.post(url, files=files, data=data, headers=headers)
+            result = response.json()
+            # Cek apakah API mengembalikan data
+            if 'data' in result and result['data']:
+                detections = result['data'][0]
+                for obj in detections:
+                    if 'bounding_box' in obj:
+                        x1, y1, x2, y2 = obj['bounding_box']
+                        countgd_box = (x1, y1, x2, y2)
+                        # Hanya tambahkan deteksi jika tidak overlap signifikan dengan YOLO
+                        if not is_overlap(countgd_box, nestle_boxes, threshold=0.3):
+                            # Gunakan label dari respons jika ada, jika tidak gunakan prompt sebagai default
+                            label = obj.get('label', prompt)
+                            competitor_class_count[label] = competitor_class_count.get(label, 0) + 1
+                            competitor_boxes.append(countgd_box)
         total_competitor = sum(competitor_class_count.values())
-        
+
         # ===== Format Output Text =====
         result_text = "Product Nestlé\n\n"
         for class_name, count in nestle_class_count.items():
             result_text += f"{class_name}: {count}\n"
         result_text += f"\nTotal Products Nestlé: {total_nestle}\n\n"
         if total_competitor:
-            result_text += "Produk Kompetitor (CountGD) :\n"
+            result_text += "Produk Kompetitor (CountGD):\n"
             for label, count in competitor_class_count.items():
                 result_text += f"{label}: {count}\n"
             result_text += f"\nTotal Produk Kompetitor: {total_competitor}\n"
         else:
             result_text += "No Unclassified Products detected\n"
-        
+
         # ===== Visualisasi =====
         img = cv2.imread(temp_path)
         # Gambar bounding box YOLO (hijau)
@@ -121,17 +125,16 @@ def detect_combined(image):
         for box in competitor_boxes:
             x1, y1, x2, y2 = box
             cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
-            # Tampilkan label hasil CountGD
             cv2.putText(img, "unclassified", (int(x1), int(y1)-10),
                         cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)
-        
+
         output_path = "/tmp/combined_output.jpg"
         cv2.imwrite(output_path, img)
         return output_path, result_text
-    
+
     except Exception as e:
         return temp_path, f"Error: {str(e)}"
-    
+
     finally:
         if os.path.exists(temp_path):
             os.remove(temp_path)
@@ -157,12 +160,14 @@ def detect_objects_in_video(video_path):
             if not video_path:
                 return None, f"Video conversion error: {err}"
 
+        # Buka video untuk diproses
         video = cv2.VideoCapture(video_path)
         frame_rate = int(video.get(cv2.CAP_PROP_FPS))
         frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
         frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
         frame_size = (frame_width, frame_height)
 
+        # Setup VideoWriter untuk output
         fourcc = cv2.VideoWriter_fourcc(*'mp4v')
         output_video = cv2.VideoWriter(temp_output_path, fourcc, frame_rate, frame_size)
 
@@ -171,11 +176,14 @@ def detect_objects_in_video(video_path):
             if not ret:
                 break
 
+            # Simpan frame untuk deteksi YOLO
             frame_path = os.path.join(temp_frames_dir, f"frame_{frame_count}.jpg")
             cv2.imwrite(frame_path, frame)
 
+            # YOLO detection pada frame
             predictions = yolo_model.predict(frame_path, confidence=50, overlap=80).json()
 
+            # Gambar deteksi YOLO pada frame
             current_detections = {}
             for prediction in predictions['predictions']:
                 class_name = prediction['class']
@@ -189,6 +197,7 @@ def detect_objects_in_video(video_path):
                 cv2.putText(frame, class_name, (pt1[0], pt1[1]-10),
                             cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 2)
 
+            # Hitung dan tampilkan jumlah deteksi pada frame
             object_counts = {}
             for detection_id in current_detections:
                 cls = current_detections[detection_id]