Re:How to Build a Real-Time Object Detection iOS App Using T...
by gok on Friday October 19, 2018 @11:20AM
(#18257298)
You're probably going to get much better performance if you convert your TensorFlow model to CoreML (use tfcoreml). Also has the advantage of not needing to compile TF for your phone yourself, and distribute it with your app.
Re:How to Build a Real-Time Object Detection iOS App Using T...
by joeblau on Friday October 19, 2018 @02:55PM
(#18259048)
I came here to say the same thing :). It's probably also easier to train using CreateML, but if you already know how to use TensorFlow then you don't really need to use CreateML.
Re:How to Build a Real-Time Object Detection iOS App Using T...
by asparagui on Friday October 19, 2018 @12:27PM
(#18257830)
Not every op supported in generic Tensorflow (software) can be converted to CoreML ops (hardware), which means a number of the more complicated models can't be automagically converted. If you have specific domain knowledge you can add substitute ops/roll your own, but this is beyond the scope of most people trying to bring models over to mobile.
Re:How to Build a Real-Time Object Detection iOS App Using T...
by natch on Friday October 19, 2018 @12:44PM
(#18257969)
Many models exist in many formats that can be converted to CoreML. So that shouldn’t be a problem. Also there is always the option of training a new model from scratch or with transfer learning.
Re:How to Build a Real-Time Object Detection iOS App Using T...
by prashp on Friday October 19, 2018 @01:50PM
(#18258538)
Actually, this is object detection because there is a bounding box which is generated localizing the object(s).
Classification would be if each frame returned a class and class score without the bounding box.
https://medium.com/jigsaw-xyz/realtime-image-recognition-in-...
(I wrote and maintain Keras-RCNN. It does not compile to CoreML. Yet.)
/pedant
Edit: /eats crow