Amazing Performance possible on iOS / Android?

gustavz / realtime_object_detection

Plug and Play Real-Time Object Detection App with Tensorflow and OpenCV

MIT License

281 stars 148 forks source link

Amazing Performance possible on iOS / Android? #16

Open madhavajay opened 6 years ago

madhavajay commented 6 years ago

I can't believe how fast this runs on my MacBook pro in CPU mode!!? Why is this not the default method of TensorFlow?

Are you able to explain how you were able to know which nodes to process on CPU and which on GPU for max performance?

Also is it possible to implement this in C++ for iOS / Android?

gustavz commented 6 years ago

@madhavajay thank you :) Yes it is possible to visualize the time each opearation consumes (for example since v2.0 with test_objectdetection.py) and from this point on it was possible to find the right splitpoints. But unfortunately this only works for ssd_mobilenet models, for other models it needs to be investigated from scratch.

madhavajay commented 6 years ago

Right but what i'm saying is will the same split points work using the C++ TF API on iOS and Android to drastically improve the performance?

gustavz commented 6 years ago

To be honest I don’t know as i did not use the c++ API yet. But I guess it should, why not.

If you try please let me know how it works :)