KerasLayer trainable = false似乎无效

Question

设置trainable = False似乎无效。

最小示例：

layer = tf.keras.layers.Dense(
      units=1,
      kernel_initializer=tf.keras.initializers.Constant([[1.0]]),
      bias_initializer=tf.keras.initializers.Constant([1.0]),
      trainable=False)
y = layer(tf.constant([[1.0]]))
with tf.Session() as session:
  session.run(tf.global_variables_initializer())
  for var in tf.global_variables():
    print("var: " + str(var) + " trainable: " + str(var.trainable))

导致：

var: <tf.Variable 'dense/kernel:0' shape=(1, 1) dtype=float32> trainable: True 
var: <tf.Variable 'dense/bias:0' shape=(1,) dtype=float32> trainable: True

我希望可训练属性设置为false。我想念什么？