starvector-text2svg-stack

<a href="" target="_blank">
<img alt="arXiv" src="https://img.shields.io/badge/arXiv-StarVector-red?logo=arxiv" height="20" />
</a>
<a href="https://starvector.github.io/" target="_blank">
<img alt="Website" src="https://img.shields.io/badge/🌎_Website-StarVector-blue.svg" height="20" />
</a>
<a href="https://github.com/joanrod/star-vector" target="_blank" style="display: inline-block; margin-right: 10px;">
<img alt="GitHub Code" src="https://img.shields.io/badge/Code-StarVector-white?&logo=github&logoColor=white" />
</a>

# Dataset Card for svg-stack-v2

## Dataset Description

This dataset contains SVG code examples for training and evaluating SVG models for image vectorization.

## Dataset Structure

### Features

The dataset contains the following fields:

| Field Name | Description |
| :--------- | :---------- |
| `Filename` | Unique ID for each SVG |
| `Svg` | SVG code |

## Usage

```python
from datasets import load_dataset

dataset = load_dataset("starvector/svg-stack-v2")
```

## Benchmark Evaluation

To evaluate your model on this dataset, please refer to the [README.md](https://github.com/joanrod/star-vector/blob/main/README.md) file in the [StarVector GitHub repository](https://github.com/joanrod/star-vector).

## Citation

```bibtex
@article{rodriguez2023starvector,
title={{StarVector: Generating Scalable Vector Graphics Code from Images and Text}},
author={Juan A. Rodriguez and Abhay Puri and Shubham Agarwal and Issam H. Laradji and Pau Rodriguez and Sai Rajeswar and David Vazquez and Christopher Pal and Marco Pedersoli},
year={2023},
journal={arXiv preprint arXiv:2312.11556},
}
```

## Tags

- scalable vector graphics (SVG)
- vision language models
- multimodal
- code

<a href="" target="_blank">
<img alt="arXiv" src="https://img.shields.io/badge/arXiv-StarVector-red?logo=arxiv" height="20" />
</a>
<a href="https://starvector.github.io/" target="_blank">
<img alt="官方网站" src="https://img.shields.io/badge/🌎_Website-StarVector-blue.svg" height="20" />
</a>
<a href="https://github.com/joanrod/star-vector" target="_blank" style="display: inline-block; margin-right: 10px;">
<img alt="GitHub 代码" src="https://img.shields.io/badge/Code-StarVector-white?&logo=github&logoColor=white" />
</a>

# svg-stack-v2 数据集卡片

## 数据集描述

本数据集包含可缩放矢量图形（Scalable Vector Graphics，SVG）代码示例，用于训练与评估面向图像矢量化任务的SVG模型。

## 数据集结构

### 字段信息

本数据集包含以下字段：

| 字段名 | 描述 |
| :--------- | :---------- |
| `Filename` | 每个SVG文件的唯一标识符 |
| `Svg` | 可缩放矢量图形（Scalable Vector Graphics，SVG）代码 |

## 使用方法

python
from datasets import load_dataset

dataset = load_dataset("starvector/svg-stack-v2")

## 基准评估

若需在本数据集上评估你的模型，请参阅[StarVector GitHub仓库](https://github.com/joanrod/star-vector)中的[README.md](https://github.com/joanrod/star-vector/blob/main/README.md)文件。

## 引用格式

bibtex
@article{rodriguez2023starvector,
title={{StarVector: Generating Scalable Vector Graphics Code from Images and Text}},
author={Juan A. Rodriguez and Abhay Puri and Shubham Agarwal and Issam H. Laradji and Pau Rodriguez and Sai Rajeswar and David Vazquez and Christopher Pal and Marco Pedersoli},
year={2023},
journal={arXiv preprint arXiv:2312.11556},
}

## 标签

- 可缩放矢量图形（Scalable Vector Graphics，SVG）
- 视觉语言模型
- 多模态
- 代码

搜集汇总

背景与挑战

背景概述

该数据集提供SVG代码示例，用于训练和评估SVG图像矢量化模型，包含文件名和SVG代码两个核心字段。它基于Apache 2.0许可证，旨在支持生成可缩放矢量图形代码的相关研究与应用。