时间戳

首页 > 解决方案 > How to use EarlyStopping to stop training when val_acc reaches a certain percentage

keras - How to use EarlyStopping to stop training when val_acc reaches a certain percentage

问题描述

I want to stop the training when it reaches a certain percentage, say 98%. I tried many ways and search on Google with no luck. What I do is using EarlyStopping like this:

es = EarlyStopping(monitor='val_acc', baseline=0.98, verbose=1)
model.fit(tr_X, tr_y, epochs=1000, batch_size=1000, validation_data=(ts_X, ts_y), verbose=1, callbacks=[es])

_, train_acc = model.evaluate(tr_X, tr_y, verbose=0)
_, test_acc = model.evaluate(ts_X, ts_y, verbose=0)
print('>> Train: %.3f, Test: %.3f' % (train_acc, test_acc))

This isn't correct. I would truly appreciate if someone can suggest a way to achieve this goal.

Thank you,

标签： keras

解决方案

你可以像这样创建一个新的回调：

class EarlyStoppingValAcc(Callback):
    def __init__(self, monitor='val_acc', value=0.98, verbose=1):
        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

并像这样使用它：

callbacks = [
             EarlyStoppingByValAcc(monitor='val_acc', value=0.98, verbose=1),
            ]
model.fit(tr_X, tr_y, epochs=1000, batch_size=1000, validation_data=(ts_X, ts_y), verbose=1, callbacks=callbacks)

推荐阅读