在Keras中使用EarlyStopping回调时如何获得最佳模型? [英] How to get the best model when using EarlyStopping callback in Keras?

问题描述

我正在使用基于val_acc和patience=0的EarlyStopping用Keras训练神经网络. EarlyStopping降低后，EarlyStopping就会停止训练.

I am training a neural network with Keras using EarlyStopping based on val_acc and patience=0. EarlyStopping stops the training as soon as val_acc decreases.

但是，我获得的最终模型不是最佳模型，即具有最高val_acc的模型.但是我宁愿有一个对应于后一个时期的模型，即对应于val_acc的那个模型仅比最佳模型低一点，从而导致提早停止！

However the final model that I obtain is not the best model, namely the one with the highest val_acc. But I rather have the model corresponding to the epoch after, namely the one corresponding to a val_acc just a bit lower than the best one and that caused the early stopping!

我如何获得最好的?

我尝试通过回叫使用保存最佳模型:

I tried to use the save the best model using the call back:

ModelCheckpoint(filepath='best_model.h5', monitor='val_loss', save_best_only=True)]

但是我得到相同的结果.

But I get the same results.

推荐答案

如果要保存最高准确度，则应将检查点monitor='val_acc'设置为自动保存在最高点.最低的损耗不一定与最高的精度相对应.您还可以设置verbose=1来查看要保存的模型以及原因.

If you would like to save the highest accuracy then you should set the checkpoint monitor='val_acc' it will automatically save on highest. Lowest loss might not necessarily correspond to highest accuracy. You can also set verbose=1 to see which model is being saved and why.

这篇关于在Keras中使用EarlyStopping回调时如何获得最佳模型?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IT屋！