Chris Sharp

Hi Michael, What phone are you using? It could be memory. Can you post a console log? I just tried that model on my iPhone 6s and it ran without...

I've seen that when I have built the iOS Tensorflow libs and forgotten to set `__ANDROID_TYPES_FULL__`. Though it is strange that 1.5 works. Using your own dataset shouldn't matter. I've...

Another thing to try is to use the -g flag to `build_all_ios.sh` . This will use `print_selective_registration_header` to look at your .pb file and output a header file containing all...

Did you every resolve this? I have a branch somewhere where I implemented portrait orientation but never pushed. I'll incorporate it into master.

Hi John, I finally got around to fixing the issue with portrait orientations. The main issue was my width and height were flipped when feeding the image data into the...

When running while attached to Xcode do you see errors in the Xcode console? Also, make sure that predictions coming out of your own graph are not all getting ignored....

It is at the top of TensorflowGraph.mm, line 15, and set to 50%. Inference scores below that value are ignored. The actual logic of ignoring anything below the threshold is...

Sorry for the delay, Did you ever figure this out? Please verify that you built the iOS libs with `ANDROID_TYPES_FULL` . I have seen errors similar to yours when loading...

It is possible the graph failed to load. Do you see any errors in the console?

If everything is running okay you should periodically see something like this in the console: `Avg. prediction time: 0.184770` To track down the problem you can try different lighting and...