Keras:我应该如何为RNN准备输入数据? [英] Keras : How should I prepare input data for RNN?

问题描述

我无法在Keras上为RNN准备输入数据.

I'm having trouble with preparing input data for RNN on Keras.

目前，我的训练数据维度为:(6752, 600, 13)

Currently, my training data dimension is: (6752, 600, 13)

• 6752:训练数据数量
• 600:时间步数
• 13:特征向量的大小(向量在浮点中)

X_train和Y_train都在这个维度上.

我想准备将此数据输入Keras的SimpleRNN中. 假设我们正在经历时间步骤，从步骤0到步骤599. 假设我要使用input_length = 5，这意味着我想使用最近的5个输入. (例如，步骤#10，#11，#12，#13，#14 @步骤#14).

I want to prepare this data to be fed into SimpleRNN on Keras. Suppose that we're going through time steps, from step #0 to step #599. Let's say I want to use input_length = 5, which means that I want to use recent 5 inputs. (e.g. step #10, #11,#12,#13,#14 @ step #14).

我应该如何重塑X_train?

应该是(6752, 5, 600, 13)还是(6752, 600, 5, 13)?

Y_train应该处于什么形状?

应该是(6752, 600, 13)还是(6752, 1, 600, 13)或(6752, 600, 1, 13)?

推荐答案

如果您只想使用最近的5个输入来预测输出，则无需提供任何训练样本的完整600个时间步长.我的建议是通过以下方式传递训练数据:

If you only want to predict the output using the most recent 5 inputs, there is no need to ever provide the full 600 time steps of any training sample. My suggestion would be to pass the training data in the following manner:

             t=0  t=1  t=2  t=3  t=4  t=5  ...  t=598  t=599
sample0      |---------------------|
sample0           |---------------------|
sample0                |-----------------
...
sample0                                         ----|
sample0                                         ----------|
sample1      |---------------------|
sample1           |---------------------|
sample1                |-----------------
....
....
sample6751                                      ----|
sample6751                                      ----------|

训练序列总数总计

(600 - 4) * 6752 = 4024192    # (nb_timesteps - discarded_tailing_timesteps) * nb_samples

每个训练序列包含5个时间步长.在每个序列的每个时间步上，您都要传递特征向量的所有13个元素.随后，训练数据的形状将为(4024192，5，13).

Each training sequence consists of 5 time steps. At each time step of every sequence you pass all 13 elements of the feature vector. Subsequently, the shape of the training data will be (4024192, 5, 13).

此循环可以重塑数据:

input = np.random.rand(6752,600,13)
nb_timesteps = 5

flag = 0

for sample in range(input.shape[0]):
    tmp = np.array([input[sample,i:i+nb_timesteps,:] for i in range(input.shape[1] - nb_timesteps + 1)])

    if flag==0:
        new_input = tmp
        flag = 1

    else:
        new_input = np.concatenate((new_input,tmp))

这篇关于Keras:我应该如何为RNN准备输入数据?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！