如何在keras中堆叠多个lstm? [英] How to stack multiple lstm in keras?

问题描述

我正在使用深度学习库keras，并尝试在没有运气的情况下堆叠多个LSTM. 下面是我的代码

I am using deep learning library keras and trying to stack multiple LSTM with no luck. Below is my code

model = Sequential()
model.add(LSTM(100,input_shape =(time_steps,vector_size)))
model.add(LSTM(100))

上面的代码在第三行Exception: Input 0 is incompatible with layer lstm_28: expected ndim=3, found ndim=2

The above code returns error in the third line Exception: Input 0 is incompatible with layer lstm_28: expected ndim=3, found ndim=2

输入X是形状的张量(100,250,50).我在tensorflow后端上运行keras

The input X is a tensor of shape (100,250,50). I am running keras on tensorflow backend

推荐答案

您需要在第一层添加return_sequences=True，以便其输出张量具有ndim=3(即批处理大小，时间步长，隐藏状态).

You need to add return_sequences=True to the first layer so that its output tensor has ndim=3 (i.e. batch size, timesteps, hidden state).

请参见以下示例:

# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(LSTM(32, return_sequences=True,
               input_shape=(timesteps, data_dim)))  # returns a sequence of vectors of dimension 32
model.add(LSTM(32, return_sequences=True))  # returns a sequence of vectors of dimension 32
model.add(LSTM(32))  # return a single vector of dimension 32
model.add(Dense(10, activation='softmax'))

来自: https://keras.io/getting-started/sequential-model -guide/(搜索"stacked lstm")

From: https://keras.io/getting-started/sequential-model-guide/ (search for "stacked lstm")

这篇关于如何在keras中堆叠多个lstm?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！