update: model

yolov8.py

@@ -171,9 +171,9 @@ def dff_nmf(image, target_lyr, n_components):
     rgb_img_float = np.float32(img) / 255.0
     input_tensor = torch.from_numpy(rgb_img_float).permute(2, 0, 1).unsqueeze(0).to(device) 
 
-    model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True).to(device)
+    model = YOLO('yolov8s.pt')
     dff= DeepFeatureFactorization(model=model,    
-                               target_layer=model.model.model.model[int(target_lyr)],    
+                               target_layer=model.model.model[int(target_lyr)],    
                                computation_on_concepts=None)
     
     concepts, batch_explanations, explanations = dff(input_tensor, model, n_components)
@@ -183,7 +183,7 @@ def dff_nmf(image, target_lyr, n_components):
        #     "https://github.com/ultralytics/yolov5/raw/master/data/coco128.yaml"  # URL to the YOLOv5 categories file
     #yaml_data = requests.get(yolov5_categories_url).text
    # labels = yaml.safe_load(yaml_data)['names']  # Parse the YAML file to get class names
-    num_classes = model.model.model.model[-1].nc 
+    num_classes = model.model.model[-1].nc 
     results = []
     for indx in range(explanations[0].shape[0]):
         upsampled_input =  explanations[0][indx]
@@ -191,7 +191,7 @@ def dff_nmf(image, target_lyr, n_components):
         device = next(model.parameters()).device
         input_tensor = upsampled_input.unsqueeze(0)
         input_tensor = input_tensor.unsqueeze(1).repeat(1, 128, 1, 1)    
-        detection_lyr = model.model.model.model[-1]
+        detection_lyr = model.model.model[-1]
         output1 = detection_lyr.m[0](input_tensor.to(device))
         objectness = output1[..., 4]  # Objectness score (index 4)
         class_scores = output1[..., 5:]  # Class scores (from index 5 onwards, representing 80 classes)