Keras回调EarlyStopping比较培训和验证损失

您可以根据需要创建自定义回调类。

我创建了一个应该符合您的需求的文件：

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))

我冒昧地解释，你想阻止如果之间的比例

train_loss

validation_loss

0.0

1.0

1.0

您可以添加一个耐心参数，该参数将等待查看阈值是否在一定时期内保持不变。

使用此方法的方法例如：

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

在这种情况下，如果训练损失保持低于

0.5*val_loss

这对您有帮助吗？