change Model API of generator

AirShower_WGAN/ShowerGAN.py

@@ -29,24 +29,25 @@ utils.plot_multiple_signalmaps(shower_maps[:,:,:,0], log_dir=log_dir, title='Foo
 
 
 # build generator
+# Feel free to modify the critic model
 def build_generator(latent_size):
-    inputs = Input(shape=(latent_size,))    
-    x = Dense(latent_size, activation='relu')(inputs)
-    x = Reshape((1,1,latent_size))(x)
-    x = UpSampling2D(size=(3,3))(x)
-    x = Conv2D(64, (2, 2), padding='same', kernel_initializer='he_normal', activation='relu')(x)
-    x = BatchNormalization()(x)
-    x = UpSampling2D(size=(3,3))(x)
-    x = Conv2D(128, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu')(x)
-    x = BatchNormalization()(x)
-    x = Conv2D(128, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu')(x)
-    x = BatchNormalization()(x)
-    x = Conv2D(256, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu')(x)
-    x = BatchNormalization()(x)
-    outputs = Conv2D(1, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu')(x)
-    return Model(inputs=inputs, outputs=outputs, name='generator')
+    generator = Sequential(name='generator')
+    generator.add(Dense(latent_size, activation='relu', input_shape=(latent_size,)))
+    generator.add(Reshape((1,1,latent_size)))
+    generator.add(UpSampling2D(size=(3,3)))
+    generator.add(BatchNormalization())
+    generator.add(UpSampling2D(size=(3,3)))
+    generator.add(Conv2D(128, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu'))
+    generator.add(BatchNormalization())
+    generator.add(Conv2D(128, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu'))
+    generator.add(BatchNormalization())
+    generator.add(Conv2D(256, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu'))
+    generator.add(BatchNormalization())
+    generator.add(Conv2D(1, (3, 3), padding='same', kernel_initializer='he_normal', activation='relu'))
+    return generator
 
 # build critic
+# Feel free to modify the critic model
 def build_critic():
     critic = Sequential(name='critic')
     critic.add(Conv2D(64, (3, 3), padding='same', kernel_initializer='he_normal', input_shape=(9,9,1)))