专栏名称: 机器学习研究会

机器学习研究会是北京大学大数据与机器学习创新中心旗下的学生组织，旨在构建一个机器学习从事者交流的平台。除了及时分享领域资讯外，协会还会举办各种业界巨头/学术神牛讲座、学术大牛沙龙分享会、real data 创新竞赛等活动。

【推荐】Instagram图片爬取、(人脸)索引与搜索

机器学习研究会 · 公众号 · AI · 2017-06-19 19:28

正文

点击上方“机器学习研究会”可以订阅哦

摘要

转自：爱可可-爱生活

I just wanted to build something cool using machine learning on a bunch of public images. But after showing it to a couple of my "friends" they thought it was too creepy and Instagram might sue me for breaking their platform policy and I should stop doing it.

So, I did what most sane people would do - write a blog post detailing how I did it, and open source it.

Whats the worst that could happen? ( ͡° ͜ʖ ͡°) > IFFSE -Instagram Facial Feature Search Engine <

What did you do?

Err.. that's a good question. I basically told a computer to download a bunch of images containing faces from Instagram, and sort them according to similarity.

Essentially building a database of indexed faces ( ͡°( ͡° ͜ʖ( ͡° ͜ʖ ͡°)ʖ ͡°) ͡°).

So how did you do it?

Before we start off doing anything machine learning-y we need a bunch of data, a bunch of #selfies to train our model on. Hmmm, sounds like we need to drop by and pay Instagram.com a visit ( ͡°╭͜ʖ╮͡° ).

Loaning Images from Instagram

I've decided to use the word 'loan' instead of scrap, as scrapping has such negative connotations with it. Anyway, I wanted a way to be able to loan images Instagram without providing them with any of my keys. After playing around with the web app for a couple of minutes, I discover the tags endpoint, which gives like infinite images without authentication.