如何在Keras中使用model.reset_states()? [英] How to use model.reset_states() in Keras?

问题描述

我有顺序数据，我声明了一个LSTM模型，该模型在Keras中用x预测y.因此，如果我调用model.predict(x1)和model.predict(x2)，在两个predict()之间显式调用model.reset_states是否正确? model.reset_states是否清除输入的历史记录，而不是权重，对吗?

I have sequential data and I declared a LSTM model which predicts y with x in Keras. So if I call model.predict(x1) and model.predict(x2), Is it correct to call model.reset_states between the two predict() explicitly? Does model.reset_states clear history of inputs, not weights, right?

# data1
x1 = [2,4,2,1,4]
y1 = [1,2,3,2,1]

# dat2
x2 = [5,3,2,4,5]
y2 = [5,3,2,3,2]

在我的实际代码中，我使用model.evaluate().在evaluate()中，是否为每个数据样本隐式调用reset_states?

And in my actual code, I use model.evaluate(). In evaluate(), is reset_states called implicitly for each data sample?

model.evaluate(dataX, dataY)

推荐答案

reset_states仅清除网络的隐藏状态.值得一提的是，取决于您的网络中是否设置了选项stateful=True-此功能的行为可能有所不同.如果未设置-网络中的每一批计算完成后，所有状态都会自动重置(例如，也调用fit，predict和evaluate之后).如果不是这样，则当您要进行连续的模型调用独立时，应每次调用reset_states.

reset_states clears only the hidden states of your network. It's worth to mention that depending on if the option stateful=True was set in your network - the behaviour of this function might be different. If it's not set - all states are automatically reset after every batch computations in your network (so e.g. after calling fit, predict and evaluate also). If not - you should call reset_states every time, when you want to make consecutive model calls independent.

这篇关于如何在Keras中使用model.reset_states()?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！