如何在 Keras 中创建自定义回调? [英] How can I create a custom callback in Keras?

问题描述

我有兴趣在拟合我的 keras 模型时创建回调.更详细地说，我想在每次 epoch 结束时从带有 val_acc 的机器人电报中收到一条消息.我知道你可以在 classifier.fit() 中添加一个 callback_list 作为参数，但是许多回调是由 keras 预先构建的，我不知道如何添加自定义的.

I'm interested in creating a callback while fitting my keras model. More in detail I'd like to receive a message from a bot telegram with val_acc each time an epoch is over. I know you can add a callback_list as a parameter in classifier.fit() but many callbacks are prebuilt by keras and I don't know how to add a custom one.

谢谢！

推荐答案

以下是我如何向回调添加验证准确性的示例:

Here is an example of how I would add validation accuracy to a callback:

class AccuracyHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.acc = []

    def on_epoch_end(self, batch, logs={}):
        self.acc.append(logs.get('val_acc'))

history = AccuracyHistory()

model.fit(x, y,
          ...
          callbacks=[history])

这篇关于如何在 Keras 中创建自定义回调?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！