ImagenHub/Subject_Driven_Image_Editing

---
configs:
- config_name: default
data_files:
- split: eval
path: data/eval-*
- split: extra
path: data/extra-*
dataset_info:
features:
- name: uid
dtype: int64
- name: image
dtype: image
- name: subject
dtype: string
splits:
- name: eval
num_bytes: 4414578.0
num_examples: 154
- name: extra
num_bytes: 1779741.0
num_examples: 66
download_size: 6179822
dataset_size: 6194319.0
---
# Dataset Card

Dataset in [ImagenHub](arxiv.org/abs/2310.01596).

# Citation

Please kindly cite our paper if you use our code, data, models or results:

```
@article{ku2023imagenhub,
title={ImagenHub: Standardizing the evaluation of conditional image generation models},
author={Max Ku and Tianle Li and Kai Zhang and Yujie Lu and Xingyu Fu and Wenwen Zhuang and Wenhu Chen},
journal={arXiv preprint arXiv:2310.01596},
year={2023}
}
```

原始信息汇总

数据集概述

配置

• 默认配置 (default)
  • 数据文件：
    • 评估集 (eval)：路径为 data/eval-*
    • 额外集 (extra)：路径为 data/extra-*

数据集信息

• 特征：
  • uid：数据类型为 int64
  • image：数据类型为 image
  • subject：数据类型为 string
• 分割：
  • 评估集 (eval)：
    • 字节数：4414578.0
    • 样本数：154
  • 额外集 (extra)：
    • 字节数：1779741.0
    • 样本数：66
• 下载大小：6179822
• 数据集大小：6194319.0