valorant-object-detection

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

### Dataset Labels

```
['dropped spike', 'enemy', 'planted spike', 'teammate']
```

### Number of Images

```json
{'valid': 1983, 'train': 6927, 'test': 988}
```

### 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/valorant-object-detection", name="full")
example = ds['train'][0]
```

### Roboflow Dataset Page
[https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3](https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3?ref=roboflow2huggingface)

### Citation

```
@misc{ valorant-9ufcp_dataset,
title = { valorant Dataset },
type = { Open Source Dataset },
author = { Daniels Magonis },
howpublished = { \\url{ https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp } },
url = { https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { nov },
note = { visited on 2023-01-27 },
}
```

### License
CC BY 4.0

### Dataset Summary
This dataset was exported via roboflow.com on December 22, 2022 at 5:10 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 9898 images.
Planted are annotated in COCO format.

The following pre-processing was applied to each image:
* Resize to 416x416 (Stretch)

No image augmentation techniques were applied.

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

### 数据集标签

['掉落的爆能器', '敌方玩家', '已布置的爆能器', '队友玩家']

### 图像数量
json
{'训练集': 6927, '验证集': 1983, '测试集': 988}

### 使用方法
- 安装[datasets库](https://pypi.org/project/datasets/)：

bash
pip install datasets

- 加载该数据集：

python
from datasets import load_dataset

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

### Roboflow 数据集页面
[https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3](https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3?ref=roboflow2huggingface)

### 引用信息

@misc{ valorant-9ufcp_dataset,
title = { 无畏契约数据集 },
type = { 开源数据集 },
author = { Daniels Magonis },
howpublished = { url{ https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp } },
url = { https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp },
journal = { Roboflow 宇宙 },
publisher = { Roboflow },
year = { 2022 },
month = { 11月 },
note = { 访问日期：2023-01-27 },
}

### 许可证
CC BY 4.0

### 数据集概览
本数据集于2022年12月22日格林尼治标准时间17:10通过roboflow.com导出。

Roboflow是一款端到端的计算机视觉平台，可助力您完成以下工作：
* 与团队协作开展计算机视觉相关项目
* 收集并整理图像素材
* 解析非结构化图像数据
* 完成图像标注并构建数据集
* 导出、训练并部署计算机视觉模型
* 通过主动学习机制随时间迭代优化数据集

该数据集共包含9898张图像，所有标注均采用COCO格式规范完成。

已对每张图像执行如下预处理操作：
* 调整至416×416分辨率（拉伸缩放）

未使用任何图像增强技术。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于《Valorant》游戏目标检测的计算机视觉数据集，包含9898张标注图像，涵盖4种游戏内对象类别。图像统一调整为416x416分辨率，采用COCO标注格式，适用于目标检测模型的训练与评估。