> For the complete documentation index, see [llms.txt](https://sharinghub.kittenbot.hk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sharinghub.kittenbot.hk/programmingplatforms/kittenblock/online/aifunctions/ml.md).

# Kittenbot機器學習

<figure><img src="/files/T4rLwedsHcve4DqSoMMI" alt=""><figcaption></figcaption></figure>

圖像辨識，姿態分類和音頻分類

## 模型訓練教學

首先打開模型訓練工具。

<figure><img src="/files/j6Ct1xNZ3LuncT0xtQOO" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/YJZ9iFCs3launTuJgkZl" alt=""><figcaption></figcaption></figure>

## 圖像辨識

在圖像辨識工具裡面，您可以使用電腦鏡頭或者上傳圖片作訓練。

在這個教學我們會試試用電腦鏡頭訓練包剪揼模型。

<figure><img src="/files/LYTbaFecd7xDblqTGfaB" alt=""><figcaption></figcaption></figure>

將分類名稱改為Rock，然後在鏡頭面前做出揼的手勢。

<figure><img src="/files/9K1xjVWdXl8XCTXszwv6" alt=""><figcaption></figcaption></figure>

按著錄製按鍵，就可以將鏡頭畫面加入樣本庫。

<figure><img src="/files/SHN566eOOptL73LmamE5" alt=""><figcaption></figcaption></figure>

重複同樣步驟，添加包的圖片樣本。

<figure><img src="/files/ht1XYhLpuZQ5HqevVjkm" alt=""><figcaption></figcaption></figure>

最後可以添加類別，完成剪的樣本錄製。

<figure><img src="/files/fvNyANqru1lgaZxoFfBQ" alt=""><figcaption></figcaption></figure>

完成後按下訓練模型，平台就會自動生成圖像辨識模型。

<figure><img src="/files/NbqJovaSWLm5SEm9jt5X" alt=""><figcaption></figcaption></figure>

訓練完成後平台會提供即時的預覽，假如效果未如理想可以繼續錄入樣本重新訓練。否則就可以按使用模型，將模型導入程式中。

<figure><img src="/files/4N2giSk51vRhUpc6Z4tA" alt=""><figcaption></figcaption></figure>

導入後，相應的編程積木就會自動生成出來。

<figure><img src="/files/maZ0haTeANi2VeI1B2az" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
儲存程式時不會儲存模型，如需保留模型請記住要儲存模型供下次使用。
{% endhint %}

<figure><img src="/files/kBHJ4gt7ltHmpmLJq82w" alt=""><figcaption></figcaption></figure>

### 參考程式

<figure><img src="/files/S6ES9vpdqFuPDGz1ny8m" alt=""><figcaption></figcaption></figure>

{% file src="/files/5XqURn1zbgMk7f9xWlrp" %}

參考模型

{% file src="/files/HqvkGcwpDZzb33iFGgDZ" %}

## 姿態分類

姿態分類是訓練模型辨識人體的姿態，訓練過程和圖像辨識相似。

<figure><img src="/files/WoTQvcaBozrJZSz4LSd6" alt=""><figcaption></figcaption></figure>

鏡頭會自動追蹤人體的頭部與四肢，因此模型訓練後即使是不同人測試，模型也能準確辨認姿勢。

<figure><img src="/files/CGjszuURC4aVC31z4GLZ" alt=""><figcaption></figcaption></figure>

### 參考程式

<figure><img src="/files/ukLkRgPWnah2ekrmqnNj" alt=""><figcaption></figcaption></figure>

{% file src="/files/QC1it84MlHUcjvnR2FcN" %}

參考模型

{% file src="/files/jiqF3tfFMzZWw6KHhwAi" %}

## 音頻分類

音頻分類可以訓練模型辨認不同的音頻。

<figure><img src="/files/EllahxOmCslKHdAwnPbz" alt=""><figcaption></figcaption></figure>

首先需要錄入背景噪音作為基準，錄入完成後按提取樣本。

<figure><img src="/files/H2Zteor3z32nbO9wTcw8" alt=""><figcaption></figcaption></figure>

錄製音頻並提取樣本。

<figure><img src="/files/cChXOmQu1mQgbcCAQY8C" alt=""><figcaption></figcaption></figure>

完成後訓練模型，平台亦會即時顯示分類結果。

<figure><img src="/files/Iv0ISGa8K2iJ4loYvz4U" alt=""><figcaption></figcaption></figure>

### 參考程式

<figure><img src="/files/xk0rLnA55B2njf0o0vv0" alt=""><figcaption></figcaption></figure>

{% file src="/files/5J12EdzKY6DWZPqIKaaa" %}

參考模型

{% file src="/files/XBzgeQHTJoA2XCQtafBr" %}

## 模型載入

如要載入先前儲存的模型，只需打開模型訓練工具然後按墮入訓練項目即可。

<figure><img src="/files/PlEL2UWdyNLPeRuIibUi" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://sharinghub.kittenbot.hk/programmingplatforms/kittenblock/online/aifunctions/ml.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.