0用于联合培训的准确性

Question

我正在尝试为到目前

1. 以下 this 模型（在TFF之外）实现收敛性和准确的结果

2. 试图将这种方法与联合框架进行集成，如下所示：

函数

def make_federated_data(client_data, client_ids):
  return [
      preprocess(client_data.create_tf_dataset_for_client(x))
      for x in client_ids]

def create_keras_model():
  return tf.keras.models.Sequential([
      tf.keras.layers.InputLayer(input_shape=(41,)),
      tf.keras.layers.Dense(82, activation='relu'),
      tf.keras.layers.Dense(41, activation='relu'),
      tf.keras.layers.Dense(1, activation= 'sigmoid')])


def model_fn():
  # We _must_ create a new model here, and _not_ capture it from an external
  # scope. TFF will call this within different graph contexts.
  keras_model = create_keras_model()
  return tff.learning.from_keras_model(
      keras_model,
      input_spec=preprocessed_example_dataset.element_spec,
      loss=tf.keras.losses.BinaryCrossentropy(),
      metrics=[tf.keras.metrics.Accuracy()])

def create_tf_dataset_for_client_fn(client_id):
      dataset = tf.data.Dataset.from_tensor_slices(train_set.to_dict("list"))
      return dataset
    
    
def create_tf_dataset_for_client_fn_2(client_id):
      dataset = tf.data.Dataset.from_tensor_slices(test.to_dict("list"))
      return dataset
    def preprocess(dataset):

def preprocess(dataset):
  def batch_format_fn(element):
    """converting each sample to an `OrderedDict` and then formatting it"""
    
    return collections.OrderedDict(
          x =  tf.reshape(tf.concat([element[i] for i in element.keys() if i!='class'],0), [-1, 41]) ,
        y = tf.reshape(element['class'], [-1, 1]))

  return dataset.repeat(5).shuffle(100, seed=1).batch(  # Repeat = number of rounds
      12).map(batch_format_fn).prefetch(10)

主

    # train_Set and test_Set are dataframes(scaled) with 41 features 
#and 1 label
    #adding client number to each sample
n_clients = 10
train_set['id'] = np.random.randint(0, n_clients ,train_set.shape[0])
test_set['id'] = np.random.randint(0, n_clients , test_set.shape[0])
# DataFrame  conversion
    train_data = tff.simulation.datasets.ClientData.from_clients_and_tf_fn(
            client_ids = list(client_ids),
            serializable_dataset_fn=create_tf_dataset_for_client_fn
        )
    
    test_data = tff.simulation.datasets.ClientData.from_clients_and_tf_fn(
            client_ids = list(client_ids),
            serializable_dataset_fn=create_tf_dataset_for_client_fn_2
        )

    # Sampling for tff
    example_dataset = train_data.create_tf_dataset_for_client(
                 train_data.client_ids[0])
    preprocessed_example_dataset = preprocess(example_dataset)
    iterative_process = tff.learning.build_federated_averaging_process(
        model_fn,
        client_optimizer_fn=lambda: tf.keras.optimizers.Adam(learning_rate=0.001),
        server_optimizer_fn=lambda: tf.keras.optimizers.Adam(learning_rate=0.001))

     federated_train_data = make_federated_data(train_data, train_data.client_ids) 

我们具有41个功能和标签。我还在这里检查了标签，并且正确地在0到1之间。 在这一点上，联合数据签名是：

<PrefetchDataset element_spec=OrderedDict([('x', TensorSpec(shape=(None, 41), dtype=tf.float32, name=None)), ('y', TensorSpec(shape=(None, 1), dtype=tf.float32, name=None))])>,
 <PrefetchDataset element_spec=OrderedDict([('x', TensorSpec(shape=(None, 41), dtype=tf.float32, name=None)), ('y', TensorSpec(shape=(None, 1), dtype=tf.float32, name=None))])>,
         ...

最后，

state = iterative_process.initialize()
NUM_ROUNDS = 10
for round_num in range(0, NUM_ROUNDS):
  state, metrics = iterative_process.next(state, federated_train_data)
  print('round {:2d}, metrics={}'.format(round_num, metrics))

上述循环的结果是每种迭代和损失的准确性0.0，并没有真正改变。
问题可能与模型和培训过程有关，因为我认为数据集的格式正确，但我无法弄清楚它是什么。
提到的结果可能表明该模型根本没有训练，而且它输出了与（0,1）完全不同的东西。
还指出，在每次迭代后，状态（模型的权重）确实会发生变化。
有什么想法吗？