如何根据损失值告诉Keras停止训练？

0 1148

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)

它告诉Keras，如果损失在2次迭代内没有改善，就停止训练。但是我要在损失小于某个恒定的“ THR”后停止训练：

if val_loss < THR:
    break

有什么建议吗？

2021-02-05 10:43 更新

anna • 5042

共 1 个回答

高赞时间

我找到了答案。我查找了Keras的资源，并找到了EarlyStopping的代码。我基于此进行了自己的回调：

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

用法：

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)