# 层空间

### 层空间

#### 激活层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/ActivationLayerSpace.java)

#### 自编码器层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/AutoEncoderLayerSpace.java)

用于自编码器的层空间

#### 批量规一化空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/BatchNormalizationSpace.java)

用于批量规一化的层空间

#### 双向的

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/Bidirectional.java)

双向层包装器。可以用同样的方式包装现有的层空间。

#### 卷积层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/ConvolutionLayerSpace.java)

用于卷积层的层空间

#### 稠密层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/DenseLayerSpace.java)

用于稠密层空间的层超参数配置空间 (多层感知器层)

#### 嵌入式层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/EmbeddingLayerSpace.java)

#### 全局池化层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GlobalPoolingLayerSpace.java)

#### 格拉夫双向长短记忆网络层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GravesBidirectionalLSTMLayerSpace.java)

用于双向长短记忆网络层的层空间

#### 格拉夫长短记忆网络层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/GravesLSTMLayerSpace.java)

用于长短记忆层的层空间

#### 长短记忆网络层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/LSTMLayerSpace.java)

用于长短记忆层的层空间

#### 基于八叉树的卷积神经网络层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/OCNNLayerSpace.java)

使用隐藏层大小代替

**numHidden**

```java
public Builder numHidden(int numHidden)
```

使用隐藏层大小代替

* 参数  numHidden
* return

#### 输出层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/OutputLayerSpace.java)

用于输出层的层超参数配置空间

#### 循环神经网络层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/RnnOutputLayerSpace.java)

循环神经网络输出层的层超参数配置空间

#### 子采样层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/SubsamplingLayerSpace.java)

用于子采样层的层超参数配置空间

#### 变分自编码层空间

[\[源码\]](https://github.com/deeplearning4j/deeplearning4j/tree/master/arbiter/arbiter-deeplearning4j/src/main/java/org/deeplearning4j/arbiter/layers/VariationalAutoencoderLayerSpace.java)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/arbiter/ceng-kong-jian.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.