News for hackers. Stuff that matters.
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 darylrowland on Friday October 19, 2018 @12:00PM (#18257650)
We wrote a similar article to this about a year ago, using CoreML & TuriCreate to train the data...

https://medium.com/jigsaw-xyz/realtime-image-recognition-in-...

Re:How to Build a Real-Time Object Detection iOS App Using T... by prashp on Friday October 19, 2018 @01:51PM (#18258548)
TuriCreate also provides good tutorials on doing this: https://apple.github.io/turicreate/docs/userguide/object_det...
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 pj_mukh on Friday October 19, 2018 @05:42PM (#18260277)
I've heard through the grapevine that Tensorflow-Lite just makes a CoreML conversion for you? Is that true?
Re:How to Build a Real-Time Object Detection iOS App Using T... by Q6T46nT668w6i3m on Friday October 19, 2018 @11:23AM (#18257322)
If, and only if, it can be compiled to CoreML.

(I wrote and maintain Keras-RCNN. It does not compile to CoreML. Yet.)

Re:How to Build a Real-Time Object Detection iOS App Using T... by minimaxir on Friday October 19, 2018 @11:46AM (#18257542)
Out of curiosity, why does compiling to CoreML fail?
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 tnolet on Friday October 19, 2018 @12:24PM (#18257802)
Reminds me of the “see/seafood” app pitched by Jian-Yang from Silicon Valley
Re:How to Build a Real-Time Object Detection iOS App Using T... by fartcannon on Friday October 19, 2018 @12:29PM (#18257850)
This is image classification, not object detection!

/pedant

Edit: /eats crow

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.
Re:How to Build a Real-Time Object Detection iOS App Using T... by kahlonel on Friday October 19, 2018 @02:15PM (#18258748)
High-performance != Real-Time
Re:How to Build a Real-Time Object Detection iOS App Using T... by 0x8BADF00D on Friday October 19, 2018 @02:33PM (#18258878)
Are they still using YOLO for object detection in TF?
Re:How to Build a Real-Time Object Detection iOS App Using T... by dizzy3gg on Friday October 19, 2018 @04:50PM (#18259958)