Update app.py

app.py

@@ -44,32 +44,44 @@ class GeneticAlgorithm:
         self.population = [self.population[i] for i in np.argsort(fitness)[-self.population_size//2:]]
 
     def crossover(self):
-        offspring = []
-        for _ in range(self.population_size//2):
-            parent1, parent2 = random.sample(self.population, 2)
-            child = Net()
-            child.fc1.set_weights((np.array(parent1.fc1.get_weights()) + np.array(parent2.fc1.get_weights())) / 2)
-            child.fc2.set_weights((np.array(parent1.fc2.get_weights()) + np.array(parent2.fc2.get_weights())) / 2)
-            child.fc3.set_weights((np.array(parent1.fc3.get_weights()) + np.array(parent2.fc3.get_weights())) / 2)
-            offspring.append(child)
-        self.population += offspring
+    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()
-                weights[0] += np.random.randn(*weights[0].shape) * 0.1
-                weights[1] += np.random.randn(*weights[1].shape) * 0.1
-                net.fc1.set_weights(weights)
-                weights = net.fc2.get_weights()
-                weights[0] += np.random.randn(*weights[0].shape) * 0.1
-                weights[1] += np.random.randn(*weights[1].shape) * 0.1
-                net.fc2.set_weights(weights)
-                weights = net.fc3.get_weights()
-                weights[0] += np.random.randn(*weights[0].shape) * 0.1
-                weights[1] += np.random.randn(*weights[1].shape) * 0.1
-                net.fc3.set_weights(weights)
-
+    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)
 # Streamlit app
 st.title("Evolution of Sub-Models")