LSTM()和LSTMCell()有什么区别?

问题描述

我已经检查了两个函数的源代码，似乎LSTM()总体上构成了LSTM网络，而LSTMCell()仅返回一个单元格.

I've checked the source code for both functions, and it seems that LSTM() makes the LSTM network in general, while LSTMCell() only returns one cell.

但是，在大多数情况下，人们在程序中仅使用一个LSTM单元.这是否意味着当您只有一个LSTM Cell(例如简单的Seq2Seq)时，调用LSTMCell()和LSTM()不会有什么区别?

However, in most cases people only use one LSTM Cell in their program. Does this mean when you have only one LSTM Cell (ex. in simple Seq2Seq), calling LSTMCell() and LSTM() would make no difference?

推荐答案

• LSTM是循环图层
• LSTMCell是LSTM层使用的对象(也恰好也是一个层)，其中包含一个步骤的计算逻辑.
• LSTM is a recurrent layer
• LSTMCell is an object (which happens to be a layer too) used by the LSTM layer that contains the calculation logic for one step.

循环图层包含一个单元格对象.该单元包含用于每个步骤的计算的核心代码，而循环层命令该单元并执行实际的循环计算.

A recurrent layer contains a cell object. The cell contains the core code for the calculations of each step, while the recurrent layer commands the cell and performs the actual recurrent calculations.

通常，人们在代码中使用LSTM层.
或者他们使用包含LSTMCell的RNN层.

Usually, people use LSTM layers in their code.
Or they use RNN layers containing LSTMCell.

两者几乎相同. LSTM层是使用LSTMCell的RNN层，您可以在源代码.

Both things are almost the same. An LSTM layer is a RNN layer using an LSTMCell, as you can check out in the source code.

关于单元格的数量:

Alghout，由于其名称，看来LSTMCell是单个单元格，实际上它是一个对象，它可以管理我们可能认为的所有单元/单元格.在提到的同一代码中，您可以看到在创建LSTMCell的实例时使用了units参数.

Alghout it seems, because of its name, that LSTMCell is a single cell, it is actually an object that manages all the units/cells as we may think. In the same code mentioned, you can see that the units argument is used when creating an instance of LSTMCell.

这篇关于LSTM()和LSTMCell()有什么区别?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！