Keras简单的RNN实现

本文介绍了Keras简单的RNN实现的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

当尝试用一个循环层编译网络时，我发现了问题.似乎第一层的维数存在一些问题，因此我对Keras中RNN层的工作方式有所了解.

I found problems when trying to compile a network with one recurrent layer. It seems there is some issue with the dimensionality of the first layer and thus my understanding of how RNN layers work in Keras.

我的代码示例是:

model.add(Dense(8,
                input_dim = 2,
                activation = "tanh",
                use_bias = False))
model.add(SimpleRNN(2,
                    activation = "tanh",
                    use_bias = False))
model.add(Dense(1,
                activation = "tanh",
                use_bias = False))

错误是

ValueError: Input 0 is incompatible with layer simple_rnn_1: expected ndim=3, found ndim=2

无论input_dim值如何，都会返回此错误.我想念什么?

This error is returned regardless of input_dim value. What am I missing ?

推荐答案

该消息表示:进入rnn的输入具有2个维，但是rnn层需要3个维.

That message means: the input going into the rnn has 2 dimensions, but an rnn layer expects 3 dimensions.

对于RNN层，您需要输入形状类似于(BatchSize, TimeSteps, FeaturesPerStep)的输入.这些是预期的3个维度.

For an RNN layer, you need inputs shaped like (BatchSize, TimeSteps, FeaturesPerStep). These are the 3 dimensions expected.

Dense层(在keras 2中)可以使用2或3维.我们可以看到您正在使用2，因为您传递了input_dim而不是传递了input_shape=(Steps,Features).

A Dense layer (in keras 2) can work with either 2 or 3 dimensions. We can see that you're working with 2 because you passed an input_dim instead of passing an input_shape=(Steps,Features).

有许多解决方法，但是最有意义和逻辑的情况是输入数据是带有时间步长的序列.

There are many possible ways to solve this, but the most meaningful and logical would be a case where your input data is a sequence with time steps.

解决方案1-您的训练数据是一个序列:

如果训练数据是序列，则可以像(NumberOfSamples, TimeSteps, Features)那样对它进行整形并将其传递给模型.确保在第一层中使用input_shape=(TimeSteps,Features)，而不是使用input_dim.

If your training data is a sequence, you shape it like (NumberOfSamples, TimeSteps, Features) and pass it to your model. Make sure you use input_shape=(TimeSteps,Features) in the first layer instead of using input_dim.

解决方案2-重塑第一个致密层的输出，使其具有附加尺寸:

model.add(Reshape((TimeSteps,Features)))

确保乘积TimeSteps*Features等于第一个密集层的输出8.

Make sure that the product TimeSteps*Features is equal to 8, the output of your first dense layer.

这篇关于Keras简单的RNN实现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！