I'll start: myself and some others have been working on a batteries-included approach for building or augmenting image datasets. Kaggle has an impressive library, but it's a bit spotty when it comes to serving my own hobbies. There have been so many ideas for tools I wanted to build, but never did because I couldn't find a prepped dataset on the Internet and didn't want to bother harvesting it myself.<p>So, what computer vision projects are y'all working on?<p>---
If you're working on a project that could benefit from readily available machine-annotated images, you can reach out here: https://gigaimager.com
kaggle's been p useful for building a baseline but i usually can't help thinking that unless i spend a significant amount of time getting my own data that i'll just end up w something everyone else already has.<p>i've been on a bit of a blackjack kick and will probably build a detector with yolo at some point. i'll likely have to scrape for card imgs and then take my own. there's probably a bunch of pretrained models online but it'll be a fun weekend side project.<p>saw this thing on twitter where ads at stadiums are tailored to customer depending on location, lots of theories on how they do it not sure if any are accurate but its p cool
<a href="https://twitter.com/haltakov/status/1415009284958703620" rel="nofollow">https://twitter.com/haltakov/status/1415009284958703620</a>