# 1.10 卷积神经网络示例（Convolutional neural network example）

简单的数字识别CNN例子：

![](/files/-Le0ccQJzmNcjUV4S3fz)

CONV层后面紧接一个POOL层，CONV1和POOL1构成第一层，CONV2和POOL2构成第二层。FC3和FC4为全连接层FC，跟标准的神经网络结构一致。最后的输出层（softmax）由10个神经元构成

整个网络各层的尺寸和参数如下表格所示：

![](/files/-Le0ccQLtzNILZ5ImTux)

池化层和最大池化层没有参数；卷积层的参数相对较少，许多参数都存在于神经网络的全连接层。随着神经网络的加深，激活值尺寸会逐渐变小，如果激活值尺寸下降太快，也会影响神经网络性能

尽量不要自己设置超参数，而是查看文献中别人采用了哪些超参数，选一个在别人任务中效果很好的架构，也可能适用于自己的应用程序

在神经网络中，另一种常见模式就是一个或多个卷积后面跟随一个池化层，然后一个或多个卷积层后面再跟一个池化层，然后是几个全连接层，最后是一个**softmax**


---

# 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/110-juan-ji-shenjing-wang-luo-shi-li-ff08-convolutional-neural-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.