started unlearning setup

architectures/Model.py

@@ -7,6 +7,7 @@ import time
 import numpy as np
 from sklearn.metrics import classification_report
 from pathlib import Path
+from unlearning.Strategy import Strategy
 
 class Model(ABC):
     def __init__(self, device, size):
@@ -92,6 +93,21 @@ class Model(ABC):
         self.model.to(self.device)
         print(f'Model loaded from {file_path}')
 
+    
+    def unlearn(self, strategy: Strategy, forget_loader, retain_loader):
+        """ Executes a targeted unlearning strategy and profiles efficiency """
+        print(f"Executing: {strategy.__class__.__name__}...")
+        
+        start_time = time.time()
+        
+        # Delegate the actual algorithmic weight/logit manipulation to the strategy
+        strategy.apply(self.network, forget_loader, retain_loader)
+        
+        elapsed_time = time.time() - start_time
+        print(f"{strategy.__class__.__name__} completed in {elapsed_time:.4f} seconds.")
+        
+        return elapsed_time
+
 
 
     # Using the factory patern here

architectures/ResNet50.py

@@ -23,14 +23,14 @@ class ResNet50(Model):
         m = models.resnet50(weights=models.ResNet50_Weights.DEFAULT)
         
         # freez all layers
-        for param in m.parameters():
-            param.requires_grad = False
+        #for param in m.parameters():
+            #param.requires_grad = False
 
         # unfreez the last two
         # NOTE: Freezing everything and unfrizing the last 3 yeilded the best performance
-        for param in m.layer2.parameters(): param.requires_grad = True
-        for param in m.layer3.parameters(): param.requires_grad = True
-        for param in m.layer4.parameters(): param.requires_grad = True
+        #for param in m.layer2.parameters(): param.requires_grad = True
+        #for param in m.layer3.parameters(): param.requires_grad = True
+        #for param in m.layer4.parameters(): param.requires_grad = True
 
         m.fc = nn.Linear(m.fc.in_features, self.size)
         return m