如何在keras中修改ModelCheckPoint以同时监视val_acc和val_loss并相应地保存最佳模型?

问题描述

ModelCheckPoint提供了分别为val_Acc和val_loss保存的选项.我想以某种方式修改它，以便val_acc在改进->保存模型.如果val_acc等于先前的最佳val_acc，则检查val_loss，如果val_loss小于先前的最佳val_loss，则保存模型.

ModelCheckPoint gives options to save both for val_Acc and val_loss separately. I want to modify this in a way so that if val_acc is improving -> save model. if val_acc is equal to previous best val_acc then check for val_loss, if val_loss is less than previous best val_loss then save the model.

    if val_acc(epoch i)> best_val_acc:
        save model
    else if val_acc(epoch i) == best_val_acc:
        if val_loss(epoch i) < best_val_loss:
           save model
        else
           do not save model

推荐答案

您可以添加两个回调:

callbacks = [ModelCheckpoint(filepathAcc, monitor='val_acc', ...),
             ModelCheckpoint(filepathLoss, monitor='val_loss', ...)]

model.fit(......., callbacks=callbacks)

使用自定义回调

您可以在LambdaCallback(on_epoch_end=saveModel)中做任何您想做的事情.

Using custom callbacks

You can do anything you want in a LambdaCallback(on_epoch_end=saveModel).

best_val_acc = 0
best_val_loss = sys.float_info.max 

def saveModel(epoch,logs):
    val_acc = logs['val_acc']
    val_loss = logs['val_loss']

    if val_acc > best_val_acc:
        best_val_acc = val_acc
        model.save(...)
    elif val_acc == best_val_acc:
        if val_loss < best_val_loss:
            best_val_loss=val_loss
            model.save(...)

callbacks = [LambdaCallback(on_epoch_end=saveModel)]

但这与具有val_acc的单个ModelCheckpoint没什么不同.除非您使用的样本很少，或者您的自定义准确性相差不大，否则您将不会真正获得相同的准确性.

But this is nothing different from a single ModelCheckpoint with val_acc. You won't really be getting identical accuracies, unless you're using very few samples, or you have a custom accuracy that doesn't vary much.

这篇关于如何在keras中修改ModelCheckPoint以同时监视val_acc和val_loss并相应地保存最佳模型?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！