models

models/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f901a7a25694ac87ad2ed3a047f5118448c23a4583a8326861daa2104c26218d
+size 6224483

requirements.txt

@@ -7,4 +7,6 @@ pydantic>=1.10.0
 python-dotenv>=1.0.0
 gradio>=4.0.0
 requests>=2.31.0
-librosa==0.10.2.post1
+librosa==0.10.2.post1
+torch
+ultralytics  

tasks/image.py

@@ -5,7 +5,7 @@ import numpy as np
 from sklearn.metrics import accuracy_score, precision_score, recall_score
 import random
 import os
-
+from ultralytics import YOLO  
 from .utils.evaluation import ImageEvaluationRequest
 from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
@@ -100,36 +100,40 @@ async def evaluate_image(request: ImageEvaluationRequest):
     # Update the code below to replace the random baseline with your model inference
     #--------------------------------------------------------------------------------------------   
     
+    model = YOLO("../models/best.pt")
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = model.to(device)    
     predictions = []
     true_labels = []
-    pred_boxes = []
-    true_boxes_list = []  # List of lists, each inner list contains boxes for one image
-    
+    pred_boxes = []  
+    true_boxes_list = []  
     for example in test_dataset:
-        # Parse true annotation (YOLO format: class_id x_center y_center width height)
+        # Extract image and annotations
+        image = example["image"]
         annotation = example.get("annotations", "").strip()
+    
         has_smoke = len(annotation) > 0
-        true_labels.append(int(has_smoke))
-        
-        # Make random classification prediction
-        pred_has_smoke = random.random() > 0.5
-        predictions.append(int(pred_has_smoke))
-        
-        # If there's a true box, parse it and make random box prediction
+        true_labels.append(1 if has_smoke else 0)
+
         if has_smoke:
-            # Parse all true boxes from the annotation
             image_true_boxes = parse_boxes(annotation)
-            true_boxes_list.append(image_true_boxes)
-            
-            # For baseline, make one random box prediction per image
-            # In a real model, you might want to predict multiple boxes
-            random_box = [
-                random.random(),  # x_center
-                random.random(),  # y_center
-                random.random() * 0.5,  # width (max 0.5)
-                random.random() * 0.5   # height (max 0.5)
-            ]
-            pred_boxes.append(random_box)
+            if image_true_boxes:
+                true_boxes_list.append(image_true_boxes)
+            else:
+                true_boxes_list.append([])
+        else:
+            true_boxes_list.append([])
+    
+        results =  model .predict(image, verbose=False)    #
+        
+        if len(results[0].boxes):
+            pred_box = results[0].boxes.xywhn[0].cpu().numpy().tolist()
+            predictions.append(1)  
+            pred_boxes.append(pred_box)
+        else:
+            predictions.append(0)  
+            pred_boxes.append([])  
+
     
     #--------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE