Update model.py

model.py

@@ -23,8 +23,8 @@ def build_embedding_network(input_shape):
     x = base_model(inputs)  # Pass input through FaceNet
 
     # Final Embedding Layer
-    x = layers.Dense(256, activation=None)(x)  # No activation before L2 norm
-    x = layers.Lambda(lambda x: tf.math.l2_normalize(x, axis=1))(x)  # L2-normalized embeddings
+    x = keras.layers.Dense(256, activation=None)(x)  # No activation before L2 norm
+    x = keras.layers.Lambda(lambda x: tf.math.l2_normalize(x, axis=1))(x)  # L2-normalized embeddings
 
     return keras.Model(inputs, x)
 
@@ -37,18 +37,18 @@ def build_siamese():
     embedding_network = build_embedding_network(input_shape)
 
 # Define inputs for the Siamese network
-    input_1 = layers.Input(input_shape)
-    input_2 = layers.Input(input_shape)
+    input_1 = keras.layers.Input(input_shape)
+    input_2 = keras.layers.Input(input_shape)
 
 # Pass inputs through the embedding network
     tower_1 = embedding_network(input_1)
     tower_2 = embedding_network(input_2)
 
 # Compute Euclidean distance between embeddings
-    distance = layers.Lambda(euclidean_distance, name='distance_layer')([tower_1, tower_2])
+    distance = keras.layers.Lambda(euclidean_distance, name='distance_layer')([tower_1, tower_2])
 
 # Custom Contrastive Output Layer
-    output = layers.Dense(1, activation='sigmoid',
+    output = keras.layers.Dense(1, activation='sigmoid',
                       kernel_regularizer=keras.regularizers.l2(1e-4))(distance)
 
 # Build the Siamese model