blood-cell-object-detection

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

### Dataset Labels

```
['platelets', 'rbc', 'wbc']
```

### Number of Images

```json
{'train': 255, 'test': 36, 'valid': 73}
```

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

### Roboflow Dataset Page
[https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu/dataset/3](https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu/dataset/3?ref=roboflow2huggingface)

### Citation

```
@misc{ blood-cell-detection-1ekwu_dataset,
title = { Blood Cell Detection Dataset },
type = { Open Source Dataset },
author = { Team Roboflow },
howpublished = { \\url{ https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu } },
url = { https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { nov },
note = { visited on 2023-01-18 },
}
```

### License
Public Domain

### Dataset Summary
This dataset was exported via roboflow.com on November 4, 2022 at 7:46 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 364 images.
Cells 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 (Stretch)

No image augmentation techniques were applied.

<div align="center">
<img width="640" alt="keremberke/血液细胞目标检测数据集" src="https://huggingface.co/datasets/keremberke/blood-cell-object-detection/resolve/main/thumbnail.jpg">
</div>

### 数据集标签

['血小板（platelets）', '红细胞（RBC）', '白细胞（WBC）']

### 图像数量

json
{"训练集": 255, "测试集": 36, "验证集": 73}

### 使用方法

- 安装[数据集（datasets）库](https://pypi.org/project/datasets/):

bash
pip install datasets

- 加载数据集:

python
from datasets import load_dataset

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

### Roboflow 数据集页面
[https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu/dataset/3](https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu/dataset/3?ref=roboflow2huggingface)

### 引用格式

@misc{ blood-cell-detection-1ekwu_dataset,
title = { 血液细胞检测数据集 },
type = { 开源数据集 },
author = { Roboflow团队 },
howpublished = { url{ https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu } },
url = { https://universe.roboflow.com/team-roboflow/blood-cell-detection-1ekwu },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { 11月 },
note = { 访问于2023年1月18日 },
}

### 许可证
公有领域（Public Domain）

### 数据集概述
本数据集于2022年11月4日格林威治标准时间19:46通过roboflow.com导出。

Roboflow是一款端到端的计算机视觉平台，可协助您：
* 与团队协作开展计算机视觉项目
* 收集并整理图像数据
* 处理非结构化图像数据
* 进行图像标注并创建数据集
* 导出、训练并部署计算机视觉模型
* 使用主动学习技术随时间迭代优化数据集

该数据集共包含364张图像，所有细胞均采用COCO格式进行标注。

以下预处理操作已应用于每张图像：
* 自动调整像素数据方向（移除EXIF方向信息）
* 拉伸缩放至416×416像素

未使用任何图像增强技术。