停止并重新开始VGG-16的培训

问题描述

我正在使用预先训练的VGG-16模型进行图像分类.我要添加自定义的最后一层，因为我的分类类别数是10.我正在训练200个时代的模型.

I am using pre-trained VGG-16 model for image classification. I am adding custom last layer as the number of my classification classes are 10. I am training the model for 200 epochs.

我的问题是:如果我在某个时期随机停止(通过关闭python窗口)培训，有什么办法，比如说时期否. 50，然后从那里继续?我已经阅读过有关保存和重新加载模型的信息，但是我的理解是，该模型仅适用于我们的自定义模型，而不适用于像VGG-16这样的预训练模型.

My question is: is there any way if I randomly stop (by closing python window) the training at some epoch, let's say epoch no. 50 and resume from there? I have read about saving and reloading model but my understanding is that works for our custom models only instead of pre-trained models like VGG-16.

推荐答案

您可以使用 ModelCheckpoint 回调以定期保存模型.要使用它，请将callbacks参数传递给fit方法:

You can use ModelCheckpoint callback to save your model regularly. To use it, pass a callbacks parameter to the fit method:

from keras.callbacks import ModelCheckpoint
checkpointer = ModelCheckpoint(filepath='model-{epoch:02d}.hdf5', ...)
model.fit(..., callbacks=[checkpointer])

然后，稍后您可以加载最后保存的模型.有关此回调的更多自定义信息，请查看文档.

Then, later you can load the last saved model. For more customization of this callback take a look at the documentation.

这篇关于停止并重新开始VGG-16的培训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！