pcb-defect-segmentation

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

### Dataset Labels

```
['dry_joint', 'incorrect_installation', 'pcb_damage', 'short_circuit']
```

### Number of Images

```json
{'valid': 25, 'train': 128, 'test': 36}
```

### 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/pcb-defect-segmentation", name="full")
example = ds['train'][0]
```

### Roboflow Dataset Page
[https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8](https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8?ref=roboflow2huggingface)

### Citation

```
@misc{ defects-2q87r_dataset,
title = { Defects Dataset },
type = { Open Source Dataset },
author = { Diplom },
howpublished = { \\url{ https://universe.roboflow.com/diplom-qz7q6/defects-2q87r } },
url = { https://universe.roboflow.com/diplom-qz7q6/defects-2q87r },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2023 },
month = { jan },
note = { visited on 2023-01-27 },
}
```

### License
CC BY 4.0

### Dataset Summary
This dataset was exported via roboflow.com on January 27, 2023 at 1:45 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 and search unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time

For state of the art Computer Vision training notebooks you can use with this dataset,
visit https://github.com/roboflow/notebooks

To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com

The dataset includes 189 images.
Defect are annotated in COCO format.

The following pre-processing was applied to each image:

No image augmentation techniques were applied.

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

### 数据集标签

['dry_joint', 'incorrect_installation', 'pcb_damage', 'short_circuit']

上述标签的中文含义分别为：虚焊（dry joint）、安装错误（incorrect installation）、印刷电路板（Printed Circuit Board，PCB）损坏、短路（short circuit）。

### 图像数量
json
{'valid': 25, 'train': 128, 'test': 36}

数据集拆分如下：验证集25张，训练集128张，测试集36张。

### 使用方法
- 安装datasets库：
bash
pip install datasets

- 加载数据集：
python
from datasets import load_dataset

ds = load_dataset("keremberke/pcb-defect-segmentation", name="full")
example = ds['train'][0]

### Roboflow 数据集页面
[https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8](https://universe.roboflow.com/diplom-qz7q6/defects-2q87r/dataset/8?ref=roboflow2huggingface)

### 引用信息
bibtex
@misc{ defects-2q87r_dataset,
title = { 缺陷数据集 },
type = { 开源数据集 },
author = { Diplom },
howpublished = { url{ https://universe.roboflow.com/diplom-qz7q6/defects-2q87r } },
url = { https://universe.roboflow.com/diplom-qz7q6/defects-2q87r },
journal = { Roboflow 开源社区 },
publisher = { Roboflow },
year = { 2023 },
month = { 1月 },
note = { 2023年1月27日访问 },
}

### 许可证
知识共享署名4.0（CC BY 4.0）

### 数据集概览
本数据集于2023年1月27日格林尼治标准时间下午1:45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项目
* 收集并整理图像数据
* 理解并检索非结构化图像数据
* 进行图像标注并构建数据集
* 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

如需使用本数据集搭配的前沿计算机视觉训练示例脚本，请访问 https://github.com/roboflow/notebooks。

如需查找超过10万个其他数据集与预训练模型，请访问 https://universe.roboflow.com。

本数据集共包含189张图像，所有缺陷目标均采用COCO格式进行标注。

已对每张图像执行以下预处理操作：

未使用任何图像增强技术。