如何将2d数组转换为keras + LSTM需要的格式 [英] How to convert 2d array into format that keras+LSTM needs

问题描述

我有一个特征trainX的5000 by 9 2d numpy数组，这些特征是一个时间序列的特征.我也有一个1d浮点要素标签trainY的numpy数组.例如，这正是您scikit-learn所需的格式.

I have a 5000 by 9 2d numpy array of features trainX which are the features of a time sequence. I also have a 1d numpy array of floating point feature labels trainY. This is exactly the format you would need for scikit-learn for example.

我想将这些与keras + LSTM一起使用.这是我目前的代码:

I would like to use these with keras+LSTM. This is my code at present:

NUM_EPOCHS = 20
model = Sequential()
model.add(LSTM(8, input_shape=(1, window_size)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=NUM_EPOCHS, batch_size=1, verbose=2)

但是，这不起作用，因为keras需要使用另一种格式的trainX.我已经阅读了手册，但我不明白这是什么.

However this doesn't work as keras needs trainX in a different format it seems. I have read the manual but I can't understand what this is exactly.

如何将我的数据转换为keras可以接受的格式?

How can I convert my data into a format that keras will accept?

推荐答案

格式为(samples, timeSteps, features)

您有多少个序列?听起来像是一个5000步的序列，对吗?

How many sequences do you have? It sounds like one sequence of 5000 steps, is that right?

则格式为(1,5000,9).

如果每个时间步长有一个标签，则标签也应为(1,5000,1). (然后使用return_sequences=True).否则，标签为(1,1).

The labels should also be (1,5000,1), if you have one label per time step. (Then use return_sequences=True). Otherwise labels are (1,1).

(可选)您可能希望将单个序列分成多个段，例如，在经典的滑动窗口情况下，例如，您想以较少的时间步长获得许多样本，例如(4998,3,1)，假设您想要一个3步骤窗口.然后标签应遵循:(4998,1).

Optionally, you may want to split your single sequence in many segments, in a classical sliding window case, for instance, where you'd have many samples with less time steps, such as (4998,3,1), supposing you want a 3-step window. Then the labels should follow: (4998,1).

这篇关于如何将2d数组转换为keras + LSTM需要的格式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！