keremberke/csgo-object-detection

---
task_categories:
- object-detection
tags:
- roboflow
- roboflow2huggingface

---

<div align="center">
<img width="640" alt="keremberke/csgo-object-detection" src="https://huggingface.co/datasets/keremberke/csgo-object-detection/resolve/main/thumbnail.jpg">
</div>

### Dataset Labels

```
['ct', 'cthead', 't', 'thead']
```

### Number of Images

```json
{'train': 3879, 'valid': 383, 'test': 192}
```

### How to Use

- Install [datasets](https://pypi.org/project/datasets/):

```bash
pip install datasets
```

- Load the dataset:

```python
from datasets import load_dataset

ds = load_dataset("keremberke/csgo-object-detection", name="full")
example = ds['train'][0]
```

### Roboflow Dataset Page
[https://universe.roboflow.com/asd-culfr/wlots/dataset/1](https://universe.roboflow.com/asd-culfr/wlots/dataset/1?ref=roboflow2huggingface)

### Citation

```
@misc{ wlots_dataset,
title = { wlots Dataset },
type = { Open Source Dataset },
author = { asd },
howpublished = { \\url{ https://universe.roboflow.com/asd-culfr/wlots } },
url = { https://universe.roboflow.com/asd-culfr/wlots },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { may },
note = { visited on 2023-01-27 },
}
```

### License
CC BY 4.0

### Dataset Summary
This dataset was exported via roboflow.com on December 28, 2022 at 8:08 PM GMT

Roboflow is an end-to-end computer vision platform that helps you
* collaborate with your team on computer vision projects
* collect & organize images
* understand unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time

It includes 4454 images.
Ct-cthead-t-thead are annotated in COCO format.

The following pre-processing was applied to each image:
* Auto-orientation of pixel data (with EXIF-orientation stripping)
* Resize to 416x416 (Fill (with center crop))

The following augmentation was applied to create 3 versions of each source image:
* Random brigthness adjustment of between -15 and +15 percent

原始信息汇总

数据集概述

任务类别

• 目标检测

标签

• ct
• cthead
• t
• thead

图像数量

• 训练集：3879张
• 验证集：383张
• 测试集：192张

使用方法

1. 安装 datasets 库： bash pip install datasets

2. 加载数据集： python from datasets import load_dataset ds = load_dataset("keremberke/csgo-object-detection", name="full") example = ds[train][0]

引用

@misc{wlots_dataset, title = {wlots Dataset}, type = {Open Source Dataset}, author = {asd}, howpublished = {url{https://universe.roboflow.com/asd-culfr/wlots}}, url = {https://universe.roboflow.com/asd-culfr/wlots}, journal = {Roboflow Universe}, publisher = {Roboflow}, year = {2022}, month = {may}, note = {visited on 2023-01-27}, }

许可证

CC BY 4.0

数据集摘要

• 数据集通过 roboflow.com 于 2022 年 12 月 28 日 20:08 GMT 导出。
• 包含 4454 张图像。
• 图像标签以 COCO 格式标注。
• 预处理步骤包括：
  • 自动调整像素方向（去除 EXIF 方向）
  • 调整大小至 416x416（中心裁剪填充）
• 数据增强包括：
  • 随机亮度调整，范围在 -15% 到 +15% 之间

搜集汇总

背景与挑战

背景概述

该数据集是一个用于CSGO（Counter-Strike: Global Offensive）游戏的目标检测数据集，包含4454张图像，标注了'ct'、'cthead'、't'和'thead'四个类别。图像经过预处理调整为416x416尺寸，并应用了随机亮度增强，以COCO格式标注，适用于训练计算机视觉模型进行玩家和头部检测。