stephanst

Joined 7 years ago

Karma
52
Submissions
44
Member since
Mar 20
I make the robots go "boop"
View on Hacker News

Recent submissions

Comment · 2 years ago
new dataset, new classes and model is yolov8 because most people prefer it. Also open weights.
Comment · 2 years ago
Yep exactly. Commercial satellite inagery isn’t great for detecting anything the size of a tank (yet) but drones will get you there. The real difficulty for detecting anything like this is the training data, IMO that’s the interesting part of the problem. The actual AI models are democratized and getting better every day, but few people focus on the training data. I have my own pipelines for generating data that I have been improving over >3 years, which I have used for commercial clients to make AI systems for specific use cases. WALDO is a way of dogfooding those data synth methods. I am constantly toying with the idea of opening up the data synth stuff as a service company or as an API, but my feeling is there is not quite enough demand yet to warrant that. This is changing very quickly though and now might be the right time…
Comment · 2 years ago
generalisation is 90% of the problem yep. This model is trained with a lot of augmentations and quite diverse data, but it still really needs fine tuning to specific use cases to get great efficiency unless you don’t care about false positives.
Comment · 2 years ago
you don’t need AI for that, classic computer vision will work fine ;)
Comment · 2 years ago
it is being used a lot for disaster response and traffic monitoring yep. Also surprisingly to me for analytics on utilisation of all kinds of infrastructure y trading firms. One of the bigger motivations to make it free was to see where people use the base model to understand whether there is a market there for a fine-tuned / more specialized version.
Comment · 2 years ago
Some of the design choices of YOLOv7 make more sense to me in the choices of default augmentations and the structures of the very large versions of the networks. I find I can push it to marginally better recall. It’s slower than Ultralytics’ V8 but if you want to do stuff like offline processing of satellite imagery for instance or get 1fps on occupancy of a parking lot that kind of performance really doesn’t matter.
Comment · 2 years ago
that class never really worked and has been removed from the new version of WALDO FYI, it’s not a military thing and shouldn’t be used as such
Comment · 2 years ago
this was >50% of the motivation
Comment · 2 years ago
Hey, thanks for posting. New release is coming tomorrow on HF BTW. AMA
Comment · 3 years ago
looks cool, thanks !

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton