Keras Callback EarlyStopping comparing training and validation loss

Question

I'm fitting a neural network in Python Keras.

To avoid overfitting I would like to monitor the training/validation loss and create a proper callback which stops computations when training loss is too much less than validation loss.

An example of a callback is:

callback = [EarlyStopping(monitor='val_loss', value=45, verbose=0, mode='auto')]

Is there any way to stop training when training loss too little compared to validation loss?

Thank you in advance

Answer 1

You can create a custom callback class for your purpose.

I have created one that should correspond to your need :

class CustomEarlyStopping(Callback):
    def __init__(self, ratio=0.0,
                 patience=0, verbose=0):
        super(EarlyStopping, self).__init__()

        self.ratio = ratio
        self.patience = patience
        self.verbose = verbose
        self.wait = 0
        self.stopped_epoch = 0
        self.monitor_op = np.greater

    def on_train_begin(self, logs=None):
        self.wait = 0  # Allow instances to be re-used

    def on_epoch_end(self, epoch, logs=None):
        current_val = logs.get('val_loss')
        current_train = logs.get('loss')
        if current_val is None:
            warnings.warn('Early stopping requires %s available!' %
                          (self.monitor), RuntimeWarning)

        # If ratio current_loss / current_val_loss > self.ratio
        if self.monitor_op(np.divide(current_train,current_val),self.ratio):
            self.wait = 0
        else:
            if self.wait >= self.patience:
                self.stopped_epoch = epoch
                self.model.stop_training = True
            self.wait += 1

    def on_train_end(self, logs=None):
        if self.stopped_epoch > 0 and self.verbose > 0:
            print('Epoch %05d: early stopping' % (self.stopped_epoch))

I took the liberty to interpret that you wanted to stop if the ratio between the train_loss and the validation_loss goes under a certain ratio threshold. This ratio argument should be between 0.0 and 1.0. However, 1.0 is dangerous as the validation loss and the training loss might fluctuate a lot in an erratic way at the beginning of the training.

You can add a patience argument which will wait to see if the breaking of your threshold is staying for a certain number of epochs.

The way to use this is for exampe :

callbacks = [CustomEarlyStopping(ratio=0.5, patience=2, verbose=1), 
            ... Other callbacks ...]
...
model.fit(..., callbacks=callbacks)

In this case it will stop if the training loss stays lower than 0.5*val_loss for more than 2 epochs.

Does that help you?