Update app.py

app.py

@@ -26,7 +26,6 @@ class Net(keras.Model):
         x = self.fc2(x)
         x = self.fc3(x)
         return x
-
 # Define a genetic algorithm class
 class GeneticAlgorithm:
     def __init__(self, population_size, task_id):
@@ -35,44 +34,37 @@ class GeneticAlgorithm:
         self.population = [Net() for _ in range(population_size)]
 
     def selection(self):
-        X_train, X_test, y_train, y_test = generate_dataset(self.task_id)
-        fitness = []
-        for i, net in enumerate(self.population):
-            net.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
-            net.build(input_shape=(None, 10))  # Compile the model before training
-            net.fit(X_train, y_train, epochs=10, verbose=0)
-            loss, accuracy = net.evaluate(X_test, y_test, verbose=0)
-            fitness.append(accuracy)
-        if len(fitness) > 0:
-            self.population = [self.population[i] for i in np.argsort(fitness)[-self.population_size//2:]]
-
+    X_train, X_test, y_train, y_test = generate_dataset(self.task_id)
+    fitness = []
+    for i, net in enumerate(self.population):
+        net.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+        net.fit(X_train, y_train, epochs=10, verbose=0)
+        loss, accuracy = net.evaluate(X_test, y_test, verbose=0)
+        fitness.append(accuracy)
+    if len(fitness) > 0:
+        self.population = [self.population[i] for i in np.argsort(fitness)[-self.population_size//2:]]
     def crossover(self):
-        offspring = []
-        X = np.random.rand(1, 10)  # dummy input to build the layers
-        for _ in range(self.population_size//2):
-            parent1, parent2 = random.sample(self.population, 2)
-            child = Net()
-            child(X)  # build the layers
-            parent1(X)  # build the layers
-            parent2(X)  # build the layers
-            
-            # Average the weights of the two parents
-            parent1_weights = parent1.get_weights()
-            parent2_weights = parent2.get_weights()
-            child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
-            child.set_weights(child_weights)
-            
-            offspring.append(child)
-        self.population += offspring
+    offspring = []
+    for _ in range(self.population_size//2):
+        parent1, parent2 = random.sample(self.population, 2)
+        child = Net()
+        child.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+        
+        # Get the weights of the parent networks
+        parent1_weights = parent1.get_weights()
+        parent2_weights = parent2.get_weights()
+        # Average the weights of the two parents
+        child_weights = [(np.array(w1) + np.array(w2)) / 2 for w1, w2 in zip(parent1_weights, parent2_weights)]
+        child.set_weights(child_weights)
+        offspring.append(child)
+    self.population += offspring
 
     def mutation(self):
-        X = np.random.rand(1, 10)  # dummy input to build the layers
-        for net in self.population:
-            net(X)  # build the layers
-            if random.random() < 0.1:
-                weights = net.get_weights()
-                new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
-                net.set_weights(new_weights)
+    for net in self.population:
+        if random.random() < 0.1:
+            weights = net.get_weights()
+            new_weights = [np.array(w) + np.random.randn(*w.shape) * 0.1 for w in weights]
+            net.set_weights(new_weights)
 
 # Streamlit app
 st.title("Evolution of Sub-Models")