tensorflow联邦: TypeError：<lambda>()接受0个位置参数，但给出了1

Question

我使用的是tensorflow-federated版本0.28。我试图实现日程安排，但是我得到了以下错误：

Traceback (most recent call last):
  File "/home/Desktop/FL/fedopt.py", line 340, in <module>
    iterative_process = build_weighted_fed_avg_with_optimizer_schedule(
  File "/home/anaconda3/envs/fl/lib/python3.9/site-packages/tensorflow_federated/python/learning/algorithms/fed_avg_with_optimizer_schedule.py", line 276, in build_weighted_fed_avg_with_optimizer_schedule
    client_work = build_scheduled_client_work(model_fn, client_learning_rate_fn,
  File "/home/anaconda3/envs/fl/lib/python3.9/site-packages/tensorflow_federated/python/learning/algorithms/fed_avg_with_optimizer_schedule.py", line 98, in build_scheduled_client_work
    whimsy_optimizer = optimizer_fn(1.0)
TypeError: <lambda>() takes 0 positional arguments but 1 was given

我的代码如下：

iterative_process = build_weighted_fed_avg_with_optimizer_schedule(
    model_fn,
    client_learning_rate_fn = lambda x: 0.001,
    client_optimizer_fn=lambda: optimizers.Adam(learning_rate= client_lr, beta_1 = 0.9, beta_2 = 0.999,epsilon = 1e-07),
    server_optimizer_fn=lambda: optimizers.SGD(learning_rate= server_lr), 
    use_experimental_simulation_loop=True)

有人能告诉我我在这里做错了什么吗？

Answer 1

在上面的代码中，lambda设置为接受参数x

client_learning_rate_fn = lambda x: 0.001

你是想通过一些x被0.001操纵，比如说乘法吗？见下文：

client_learning_rate_fn = lambda x: x*0.001

编辑:修正语法错误