tensorflow联邦学习后的Keras模型预测

Question

我正在使用TensorFlow联邦框架，并为二进制分类问题设计了一个keras模型。我用tff.learning.build_federated_averaging_process定义了迭代过程，用state, metrics = iterative_process.next(state, train_data)广播了模型。

在执行上述步骤之后，我尝试运行预测，

    model_test=create_keras_model() # function defining the binary classification model
    model_test.compile(optimizer='adam',            
    loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
                metrics=['accuracy'])
    pred_out=model_test.predict(a[0].take(20)) # a[0] is the dataset constructed with the function 
                                             create_tf_dataset_for_client()
    classes =( pred_out >0.5 ).astype("int32")
    np.unique(classes)

    array([[0],
       [1],
       [0],
       [0],
       [1],
       [1],
       [1],
       [0],
       [0],
       [1],
       [1],
       [0],
       [1],
       [1],
       [0],
       [0],
       [0],
       [1],
       [1],
       [0]], dtype=int32)

但是，在将tff学习模型的状态权值应用到模型中后，预测结果并不如预期的那样工作。它对所有行都显示相同的值。

    model_test=create_keras_model() # function defining the binary classification model
    state.model.assign_weights_to(model_test)
    pred_out=model_test.predict(a[0].take(20)) # a[0] is the dataset constructed with the function 
                                             create_tf_dataset_for_client()
    print(pred_out)

    array([[-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368],
       [-0.2798368]], dtype=float32)

在连续的研究中，我知道上面的值'-0.2798368‘是状态模型权重中的值。

    print(state.model.assign_weights_to(keras_model))
    ModelWeights(trainable=[array([[-4.984627  , -5.193449  , -5.790202  , 
    -5.5200233 , -5.5461893 ,
    -4.977145  , -5.4065394 , -5.619186  , -5.3337646 , -5.136057  ],
    [-0.5657665 , -5.8657775 , -5.3425145 , -5.2261133 , -5.330576  ,
    -5.9684296 , -5.4551187 , -5.3567815 , -4.8706098 , -5.7063856 ],
    [-5.6153154 , -5.9375963 , -5.4587545 , -5.689524  , -5.463484  ,
    -4.9066486 , -5.752383  , -0.3759068 , -5.4120364 , -5.8245053 ],
    [-5.2911777 , -5.42058   , -5.932811  , -5.4922986 , -0.41761395,
    -5.432293  , -5.309703  ,  0.31641293, -5.635701  , -5.7644367 ],
    [ 0.07086992, -5.0122833 , -5.2278    , -5.2102866 , -0.03762579,
    -0.43286362, -4.865974  , -0.3707862 , -5.9437294 , -5.1678157 ],
    [-5.6853213 , -5.467271  , -5.7508802 , -5.4324217 , -5.3518825 ,
    -5.033523  , -4.8834076 , -4.8871975 , -5.9014115 , -5.3266053 ],
    [-5.280035  , -5.763103  , -5.828321  , -5.780304  , -5.908666  ,
    -5.6955295 , -5.6714606 , -4.9686913 , -4.898386  , -5.12075   ],
    [-4.8388877 , -5.7745824 , -5.1134114 , -5.779592  , -5.616187  ,
    -4.870717  , -5.131807  , -5.9274936 , -5.345783  , -5.113287  ]],
    dtype=float32), array([-5.4049463, -5.4049444, -5.404945 , -5.404946 , 
    -5.404945 ,
    -5.4049444, -5.404945 , -5.404945 , -5.4049454, -5.4049444],
    dtype=float32), array([[ 4.972922 ],
    [-4.823935 ],
    [ 4.916144 ],
    [ 5.0096955],
    [-4.9212008],
    [-5.1436653],
    [ 4.8211393],
    [-4.8939514],
    [ 5.1752467],
    [-5.01398  ]], dtype=float32), **array([-0.2798368]**, dtype=float32)], 
    non_trainable=[])

tff.learning.build_federated_averaging_process

• ，我们是否需要显式地将状态模型权重应用于服务器模型，还是

1. 会在默认情况下负责更新服务器模型？tff教程中给出了“通过使用服务器优化器的tf.keras.optimizers.Optimizer.apply_gradients方法在服务器上应用聚合模型增量”

。

在这里有什么指导/建议，因为我哪里出错了？

Answer 1

我们可能需要后退一步，考虑一下系统模型是如何联合计算的，以便在某个时候理解“服务器模型”的含义。SERVER和CLIENTS概念存在于脚本正在执行的python运行时的不同抽象层中。这意味着在Python中构造Keras模型的代码“在”具有这些位置概念的“联邦上下文”之外。

# TFF doesn't know about this model, it doesn't exist at a "placement",
# i.e. it is neither SERVER nor CLIENTS placed.
model = create_keras_model()

learning_process = tff.learning.build_federated_averaging_process(...)
# During the call to `initialize` a "federated context" exists, which runs
# a `tff.Computation` called `initialize` that creates a value placed at 
# SERVER. However, once the function "returns back to Python", the "state"
# variable we have below no longer has any "placement", its just "in Python".
state = learning_process.initialize()
# When we pass "state" back into the `next` method, it is given placement again
# based on the type signature of `next`. In this case, its placed back at 
# SERVER and the placement is used _during_ the invocation of `next`. Again,
# once `next` returns, the notion of placements goes away; we're back "in 
# Python" without placement.
state, metrics = learning_process.next(state, data)

在上面的代码中，model可以被称为“服务器模型”，它最初将具有相同的权重，但它不是TFF API文档中提到的SERVER放置模型。文档仅引用在调用tff.Computation期间的值(例如，initialize和next)。

换句话说，model和state没有连接。更新一个不会更新另一个。使用model与新训练的权重(例如，在next调用之后)。代码必须将state权重分配回model (如问题中所做的那样)：

state.model.assign_weights_to(model)