Update app.py

app.py

@@ -45,43 +45,44 @@ class GeneticAlgorithm:
 
     def crossover(self):
         offspring = []
-    for _ in range(self.population_size//2):
-        parent1, parent2 = random.sample(self.population, 2)
-        child = Net()
-        
-        # Average the weights of the two parents
-        parent1_weights = parent1.fc1.get_weights()
-        parent2_weights = parent2.fc1.get_weights()
-        child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
-        child.fc1.set_weights(child_weights)
-        
-        parent1_weights = parent1.fc2.get_weights()
-        parent2_weights = parent2.fc2.get_weights()
-        child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
-        child.fc2.set_weights(child_weights)
-        
-        parent1_weights = parent1.fc3.get_weights()
-        parent2_weights = parent2.fc3.get_weights()
-        child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
-        child.fc3.set_weights(child_weights)
-        
-        offspring.append(child)
-    self.population += offspring
+        for _ in range(self.population_size//2):
+            parent1, parent2 = random.sample(self.population, 2)
+            child = Net()
+            
+            # Average the weights of the two parents
+            parent1_weights = parent1.fc1.get_weights()
+            parent2_weights = parent2.fc1.get_weights()
+            child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
+            child.fc1.set_weights(child_weights)
+            
+            parent1_weights = parent1.fc2.get_weights()
+            parent2_weights = parent2.fc2.get_weights()
+            child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
+            child.fc2.set_weights(child_weights)
+            
+            parent1_weights = parent1.fc3.get_weights()
+            parent2_weights = parent2.fc3.get_weights()
+            child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
+            child.fc3.set_weights(child_weights)
+            
+            offspring.append(child)
+        self.population += offspring
 
     def mutation(self):
         for net in self.population:
-        if random.random() < 0.1:
-            weights = net.fc1.get_weights()
-            new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
-            net.fc1.set_weights(new_weights)
-            
-            weights = net.fc2.get_weights()
-            new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
-            net.fc2.set_weights(new_weights)
-            
-            weights = net.fc3.get_weights()
-            new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
-            net.fc3.set_weights(new_weights)
+            if random.random() < 0.1:
+                weights = net.fc1.get_weights()
+                new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
+                net.fc1.set_weights(new_weights)
+                
+                weights = net.fc2.get_weights()
+                new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
+                net.fc2.set_weights(new_weights)
+                
+                weights = net.fc3.get_weights()
+                new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
+                net.fc3.set_weights(new_weights)
+
 # Streamlit app
 st.title("Evolution of Sub-Models")