chest-xray-classification

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

### Dataset Labels

```
['NORMAL', 'PNEUMONIA']
```

### Number of Images

```json
{'train': 4077, 'test': 582, 'valid': 1165}
```

### 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/chest-xray-classification", name="full")
example = ds['train'][0]
```

### Roboflow Dataset Page
[https://universe.roboflow.com/mohamed-traore-2ekkp/chest-x-rays-qjmia/dataset/2](https://universe.roboflow.com/mohamed-traore-2ekkp/chest-x-rays-qjmia/dataset/2?ref=roboflow2huggingface)

### Citation

```

```

### License
CC BY 4.0

### Dataset Summary
This dataset was exported via roboflow.ai on March 31, 2022 at 3:11 PM GMT

It includes 5824 images.
Pneumonia are annotated in folder format.

The following pre-processing was applied to each image:
* Auto-orientation of pixel data (with EXIF-orientation stripping)
* Resize to 640x640 (Stretch)

No image augmentation techniques were applied.

<div align="center">
<img width="640" alt="keremberke/胸部X光片分类（chest-xray-classification）" src="https://huggingface.co/datasets/keremberke/chest-xray-classification/resolve/main/thumbnail.jpg">
</div>

### 数据集标签

['正常（NORMAL）', '肺炎（PNEUMONIA）']

### 图像数量
json
{'训练集': 4077, '测试集': 582, '验证集': 1165}

### 使用方法
- 安装[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/chest-xray-classification", name="full")
example = ds['train'][0]

### Roboflow数据集页面
[https://universe.roboflow.com/mohamed-traore-2ekkp/chest-x-rays-qjmia/dataset/2](https://universe.roboflow.com/mohamed-traore-2ekkp/chest-x-rays-qjmia/dataset/2?ref=roboflow2huggingface)

### 引用

### 许可证
CC BY 4.0

### 数据集概述
本数据集于2022年3月31日格林尼治标准时间15:11通过roboflow.ai导出。
共包含5824张图像。
数据集内的肺炎样本采用文件夹格式完成标注。
已对每张图像执行以下预处理操作：
* 像素数据自动校正（移除EXIF方向元数据）
* 拉伸缩放至640×640像素
未使用任何图像增强技术。