Tensorflow图像生成文本实现（1）flickr30k数据集介绍

flickr30k数据集是什么

这个数据集的核心就两点，一是图像，二是图像对应的描述语言。
先上图：

在token文件中的标注信息：
667626.jpg#0 A girl wearing a red and multicolored bikini is laying on her back in shallow water .
667626.jpg#1 Girl wearing a bikini lying on her back in a shallow pool of clear blue water .
667626.jpg#2 A young girl is lying in the sand , while ocean water is surrounding her .
667626.jpg#3 A little girl in a red swimsuit is laying on her back in shallow water .
667626.jpg#4 A girl is stretched out in shallow water

可以看到，每副图像都搭配有5句描述，五句描述语言的的意思基本都差不多。
我们的目标是训练出一个模型，需要达到的效果是：将一张图像放进去，出来一句对应的还算正确的图像描述，俗话说的看图说话。

数据集下载

官网传送门：点我点我

在本页最下面填个表，然后就可以下载了，但是，有大概率很慢而且不稳定。
百度云链接：链接: https://pan.baidu.com/s/1nQ_t-OzuFkxJmfbzRH2vPA 提取码: md6z （链接失效请留言）

数据集文件结构

两个tar压缩包

1. flickr30k-images.tar
2. flickr30k.tar.gz

第一个包存放图片，第二个包存放图像的标注信息（一张图像有几句语言表述）。
在 flickr30k.tar.gz 中，有一个名为 results_20130124.token，可以输入该文件进行查看。

import pandas as pd

annotations = pd.read_table('results_20130124.token', sep='\t', header=None,
                            names=['image', 'caption'])
print(annotations)

结果为：

                   image                                            caption
0       1000092795.jpg#0  Two young guys with shaggy hair look at their ...
1       1000092795.jpg#1  Two young , White males are outside near many ...
2       1000092795.jpg#2   Two men in green shirts are standing in a yard .
3       1000092795.jpg#3       A man in a blue shirt standing in a garden .
4       1000092795.jpg#4            Two friends enjoy time spent together .
5         10002456.jpg#0  Several men in hard hats are operating a giant...
6         10002456.jpg#1  Workers look down from up above on a piece of ...
7         10002456.jpg#2   Two men working on a machine wearing hard hats .
8         10002456.jpg#3              Four men on top of a tall structure .
9         10002456.jpg#4                         Three men on a large rig .
...                  ...                                                ...
[158915 rows x 2 columns]

可以看出一张图像，对应5条描述语言，一共有158915条语言描述。