Really nifty
That the app works at all and as fast as it does is simply amazing. When I show it to my engineering friends their jaws literally drop.
When I show it to people with less engineering background their reaction is an amusing “so what”
Would it be helpful to have a user feedback mechanism to help train the models?
For example it identifies toy dinosaurs as “dog”
Also it identifies pictures of people as people.
When I show it to people with less engineering background their reaction is an amusing “so what”
Would it be helpful to have a user feedback mechanism to help train the models?
For example it identifies toy dinosaurs as “dog”
Also it identifies pictures of people as people.
Show less
Amazing!
It’s like a bit of magic on my iPhone XR.
Awesome!
This app works great! The FPS raises and lowers as more objects come into view, but they fixed that with max items slider with 1 objects detected at a time to 100! So great job developers!
Change resolution
Hi really good work.
But I want to try change image resolution and to see the performance. How does it happen?
But I want to try change image resolution and to see the performance. How does it happen?
Response from developer
Thank you!! We are now packaging the app with both YOLOv3-SPP and YOLOv3-tiny. Tiny should feature faster FPS. Actual changes to the inference shape at runtime should theoretically be possible using CoreML flexible input sizes, though we haven't succeeded in this so far. Help is welcome if you are an iOS developer!
On Point!!!
Great work.
Response from developer
Thank you!!
