python - 无法将多个回调传递给 keras 模型

Question

我正在构建一个 keras LSTM 模型，在第一次通过时我发现它有点过度拟合数据，所以我初始化了 2 个回调 - 一个用于控制可变学习率，另一个用于允许提前停止:

    def _initialise_callback(self):

        # Ensure learning rate decreases with the epoch number
        learning_rate = 0.1
        decay_rate = learning_rate / self.epochs
        momentum = 0.8
        self.sgd = SGD(lr=learning_rate, momentum=momentum, decay=decay_rate, nesterov=False)

        #Allow model to stop early to prevent overfitting
        self.early_stopping = EarlyStopping(monitor='loss', patience=3)

但出于某种原因，我似乎无法将它们都传递给 fit() 方法。我所做的是:

    def fit(self):
        self.model.fit(self.train_set, epochs=self.epochs, verbose=2, shuffle=False,
                       callbacks=[self.early_stopping, self.sgd],
                       use_multiprocessing=False)

这会导致以下错误:

  File "<ipython-input-1-1532e4234d2a>", line 1, in <module>
    runfile('C:/VULCAN_HOME/sampling_bias/bias_LSTM.py', wdir='C:/VULCAN_HOME/sampling_bias')

  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
    execfile(filename, namespace)

  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "C:/VULCAN_HOME/sampling_bias/bias_LSTM.py", line 174, in <module>
    predictor.fit()

  File "C:/VULCAN_HOME/sampling_bias/bias_LSTM.py", line 164, in fit
    use_multiprocessing=False)

  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1147, in fit
    initial_epoch=initial_epoch)

  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)

  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
    initial_epoch=initial_epoch)

  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 100, in fit_generator
    callbacks.set_model(callback_model)

  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\callbacks\callbacks.py", line 68, in set_model
    callback.set_model(model)

AttributeError: 'SGD' object has no attribute 'set_model'

另一方面，如果我尝试仅传递 sgd 或仅传递 early_stopping 那么一切正常。有人知道这里发生了什么吗？

Answer 1

SGD 优化器应作为参数传递给 compile 方法，如图所示 here而不是作为 fit 方法的回调参数。我已经在下面修改了您的代码:

def fit(self):
        self.model.fit(self.train_set, epochs=self.epochs, verbose=2, shuffle=False,
                       callbacks=[self.early_stopping],
                       use_multiprocessing=False)

当你编译模型时通过你的优化器

self.model.compile(optimizer=self.sgd, **kwargs)