changed batch size

tasks/image.py

@@ -16,7 +16,7 @@ load_dotenv()
 router = APIRouter()
 
 #MODEL_TYPE = "YOLOv11n"
-DESCRIPTION = f"YOLOv11n model 1280 with batch 64 inference"
+DESCRIPTION = f"YOLOv11n model 1280 with batch 16 inference"
 ROUTE = "/image"
 
 def parse_boxes(annotation_string):
@@ -123,7 +123,7 @@ async def evaluate_image(request: ImageEvaluationRequest):
     INFERENCE_ENGINE_TYPE = 'pt'
     INPUT_SIZE = 1280
     N_TEST_BATCHES = 2
-    BATCH_SIZE = 64 # Can be adjusted as needed
+    BATCH_SIZE = 16 # Can be adjusted as needed
 
     def preprocessor(frame):
         #frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) # Only when read from file
@@ -301,21 +301,20 @@ async def evaluate_image(request: ImageEvaluationRequest):
     emissions_data = tracker.stop_task()
     predictions = all_binary_classifications
     # Calculate classification metrics
-    print("true_labels", true_labels)
-    print("predictions", predictions)
     classification_accuracy = accuracy_score(true_labels, predictions)
     classification_precision = precision_score(true_labels, predictions)
     classification_recall = recall_score(true_labels, predictions)
     
     # Calculate mean IoU for object detection (only for images with smoke)
     # For each image, we compute the max IoU between the predicted box and all true boxes
+    print("Calculating mean IoU")
     ious = []
     for true_boxes, pred_box in zip(true_boxes_list, pred_boxes):
         max_iou = compute_max_iou(true_boxes, pred_box)
         ious.append(max_iou)
     
     mean_iou = float(np.mean(ious)) if ious else 0.0
-    
+    print("Mean IoU calculated")    
     # Prepare results dictionary
     results = {
         "username": username,
@@ -336,5 +335,5 @@ async def evaluate_image(request: ImageEvaluationRequest):
             "test_seed": request.test_seed
         }
     }
-    
+    print("Result returned")
     return results