# 1.8 简单卷积网络示例（A simple convolution network example）

简单的CNN网络模型：

![](https://2314428465-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-Le0cHhI0S0DK8pwlrmD%2F-Le0cKOp1vaxoORIi4ak%2F-Le0cUhTOMrAQg-f8X8E%2F4545import.png?generation=1556953087114367\&alt=media)

$$a^{\[3]}$$的维度是7 x 7 x 40，将$$a^{\[3]}$$排列成1列，维度为1960 x 1，然后连接最后一级输出层。输出层可以是一个神经元，即二元分类（logistic）；也可以是多个神经元，即多元分类（softmax）。最后得到预测输出$$\hat y$$

随着CNN层数增加，$$n\_H^{\[l]}$$和$$n\_W^{\[l]}$$一般逐渐减小，而$$n\_c^{\[l]}$$一般逐渐增大

CNN有三种类型的layer：

* **Convolution层（CONV）**
* **Pooling层（POOL）**
* **Fully connected层（FC）**

CONV最为常见也最重要


---

# 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://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/foundations-of-convolutional-neural-networks/18-jian-dan-juan-ji-wang-luo-shi-li-ff08-a-simple-convolution-network-example.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.