lmms-lab/TextCaps

---
dataset_info:
features:
- name: question_id
dtype: string
- name: question
dtype: string
- name: image
dtype: image
- name: image_id
dtype: string
- name: image_classes
sequence: string
- name: flickr_original_url
dtype: string
- name: flickr_300k_url
dtype: string
- name: image_width
dtype: int64
- name: image_height
dtype: int64
- name: set_name
dtype: string
- name: image_name
dtype: string
- name: image_path
dtype: string
- name: caption_id
sequence: int64
- name: caption_str
sequence: string
- name: reference_strs
sequence: string
splits:
- name: train
num_bytes: 6201208209.0
num_examples: 21953
- name: val
num_bytes: 919878416.0
num_examples: 3166
- name: test
num_bytes: 959971875.0
num_examples: 3289
download_size: 8064165124
dataset_size: 8081058500.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: val
path: data/val-*
- split: test
path: data/test-*
---

<p align="center" width="100%">
<img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%">
</p>

# Large-scale Multi-modality Models Evaluation Suite

> Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval`

🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co/lmms-lab)

# This Dataset

This is a formatted version of [TextCaps](https://textvqa.org/textcaps/). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models.

```
@inproceedings{sidorov2019textcaps,
title={TextCaps: a Dataset for Image Captioningwith Reading Comprehension},
author={Sidorov, Oleksii and Hu, Ronghang and Rohrbach, Marcus and Singh, Amanpreet},
journal={European Conference on Computer Vision},
year={2020}
}
```

原始信息汇总

数据集概述

数据集信息

特征

• question_id: 字符串类型
• question: 字符串类型
• image: 图像类型
• image_id: 字符串类型
• image_classes: 字符串序列
• flickr_original_url: 字符串类型
• flickr_300k_url: 字符串类型
• image_width: 64位整数类型
• image_height: 64位整数类型
• set_name: 字符串类型
• image_name: 字符串类型
• image_path: 字符串类型
• caption_id: 64位整数序列
• caption_str: 字符串序列
• reference_strs: 字符串序列

数据分割

• train:
  • 字节数: 6201208209.0
  • 样本数: 21953
• val:
  • 字节数: 919878416.0
  • 样本数: 3166
• test:
  • 字节数: 959971875.0
  • 样本数: 3289

数据集大小

• 下载大小: 8064165124
• 数据集大小: 8081058500.0

配置

• config_name: default
  • 数据文件:
    • train: data/train-*
    • val: data/val-*
    • test: data/test-*