iOS machine learning platform moves into beta
1–6 of 6 posts
Re: iOS machine learning platform moves into beta
#2This looks interesting! A couple questions:
How does this compare to CoreML? What are the advantages of running models on-device vs in the cloud via an API?
Re: iOS machine learning platform moves into beta
#3This looks interesting! A couple questions: How does this compare to CoreML? What are the advantages of running models on-device vs in the cloud via an API?
Skafos actually leverages CoreML and the models do run on device. It's a live update to device local models in the background, or even hot swap while in the foreground.
Re: iOS machine learning platform moves into beta
#4TL;DR value prop:
1. Push for coreML - live update apps with models, approve your app w/ Apple just once
2. Heavy metal for training your coreML models - createML on a laptop stops making sense pretty fast
Re: iOS machine learning platform moves into beta
#5This looks interesting! A couple questions: How does this compare to CoreML? What are the advantages of running models on-device vs in the cloud via an API?
Not all models need to run on the device - of course. BUT there are a few that make a lot of sense. It all depends on speed and what you want to offload to the device. Example, a more quickly responsive (even when offline) image classification (eg is this poison ivy or not) model is best on device. Or in an AR-kit app. Or privacy, like not wanting to ship a medical image across the pipe and so on.
Re: iOS machine learning platform moves into beta
#6This looks really cool! If you need a tool like that on both Android and iOS, I had a great experience with Fritz.
http://fritz.ai