# Data Set For NXP AIM

In NXP AIM 2024, we will be working on following traffic signs:

1. Go Straight Traffic Sign
2. Turn Left Traffic Sign
3. Turn Right Traffic Sign
4. Stop Traffic sign

{% hint style="danger" %}
Teams have to divide the dataset into train/validation/test sub-sets on their own.
{% endhint %}

## Traffic Sign Designs

{% hint style="info" %}
Teams can add more images to the data set as per their needs by refering to images of finalised traffic sign design in below file
{% endhint %}

{% file src="/files/6PNgpmPpxhmpJRO4Gu9V" %}
Traffic Sign Designs and sizes
{% endfile %}

## Unlabbled data set

The below file conatins all the images that can be used in training of your model are present here.

{% file src="/files/E915IJtP5YDI9SndhajD" %}
Unlabbled data set
{% endfile %}

## Labbled/bounded data set

The below file conatins all the images along with information about their labels and clases that can be used in training of ypur model are present here.

{% file src="/files/eT49f5QRPVmHhlpXuP0h" %}
Labbled data set for Pytorch
{% endfile %}

{% file src="/files/JROREeGfaxFO7VL1L76l" %}
Labbled data set for OBB (Tensorflow)
{% endfile %}

{% hint style="warning" %}
Teams need to devide the images into train,val and test categories themselves and then create suiatble folders and edit this yaml file
{% endhint %}

## Labbled/bounded data set (Advance: multi class images)

The below links contain file containing images with multiple signs classes in a single image along with information about their labels and clases that can be used in training of ypur model are present here.

Labbled data set for Pytorch - [Pytorch\_Dataset\_Multi\_Class\_Images](https://drive.google.com/file/d/1Pwdfj1s_jhs9N_B77LSnsnRJK8ORZWJm/view?usp=drive_link).

Labbled data set for OBB (Tensorflow) - [OBB\_Dataset\_Multi\_Class\_Images](https://drive.google.com/file/d/1JbPie3vatNqR2R2F6WIC3U8Yc5u3qaJA/view?usp=drive_link).

{% hint style="warning" %}
Teams need to devide the images into train,val and test categories themselves and then create suiatble folders and edit this yaml file
{% endhint %}

## Unlabbled data set for Traffic Light

The below links conatins all the images that can be used in training of your model to detect the Traffic Light to be used in AIM Grand finale.

Unlabbled data set for red/green light - [Traffic\_Light\_Imahes](https://drive.google.com/file/d/1yABED6JG6RhJK6PuLO4kyX2o93KiAB4Y/view?usp=drive_link).

{% hint style="warning" %}
The link contains 1700+ red lights and 700+ green light images. We recommend all participants only to train model for red traffic light and consider it an extension of stop sign.
{% endhint %}

## Labbled data set for Traffic Signs and Traffic Lights

The below links conatins all the images that can be used in training of your model to detect the Traffic Light as well as traffic lights to be used in AIM Grand finale.

Final labbled data set - [Final Dataset](https://drive.google.com/file/d/1lqwVEBoE3GSfqYYgdWikSVWGg064E3O-/view?usp=drive_link).

{% hint style="warning" %}
This is updated dataset for traffic signs as well as traffic lights. In this data set there are more images, as well as the bounding boxes are improved to achieve better results
{% endhint %}


---

# 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://nxp.gitbook.io/nxp-aim/dataset.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.