目前我使用以下代码：

callbacks = [    EarlyStopping(monitor='val_loss', patience=2, verbose=0),    ModelCheckpoint(kfold_weights_path, monitor='val_loss', save_best_only=True, verbose=0),]model.fit(X_train.astype('float32'), Y_train, batch_size=batch_size, nb_epoch=nb_epoch,      shuffle=True, verbose=1, validation_data=(X_valid, Y_valid),      callbacks=callbacks)

这段代码告诉Keras，当损失值在连续两个epoch内没有改善时停止训练。但我想在损失值小于某个常数“THR”后停止训练：

if val_loss < THR:    break

我在文档中看到可以创建自己的回调函数：http://keras.io/callbacks/但没有找到如何停止训练过程的具体方法。我需要一些建议。

回答：

我找到了答案。我查看了Keras的源代码，发现了EarlyStopping的实现代码。我基于它创建了自己的回调函数：

class EarlyStoppingByLossVal(Callback):    def __init__(self, monitor='val_loss', value=0.00001, verbose=0):        super(Callback, self).__init__()        self.monitor = monitor        self.value = value        self.verbose = verbose    def on_epoch_end(self, epoch, logs={}):        current = logs.get(self.monitor)        if current is None:            warnings.warn("Early stopping requires %s available!" % self.monitor, RuntimeWarning)        if current < self.value:            if self.verbose > 0:                print("Epoch %05d: early stopping THR" % epoch)            self.model.stop_training = True

使用方法如下：

callbacks = [    EarlyStoppingByLossVal(monitor='val_loss', value=0.00001, verbose=1),    # EarlyStopping(monitor='val_loss', patience=2, verbose=0),    ModelCheckpoint(kfold_weights_path, monitor='val_loss', save_best_only=True, verbose=0),]model.fit(X_train.astype('float32'), Y_train, batch_size=batch_size, nb_epoch=nb_epoch,      shuffle=True, verbose=1, validation_data=(X_valid, Y_valid),      callbacks=callbacks)