Incorrect results, mostly predicting 'box turtle' and 'cd player' for every image.

hollance / Inception-CoreML

Running Inception-v3 on Core ML

98 stars 28 forks source link

Incorrect results, mostly predicting 'box turtle' and 'cd player' for every image. #4

Open hassanmasood1 opened 6 years ago

hassanmasood1 commented 6 years ago

I am using your project with xcode 10 beta on ios 11. Not sure if there is an issue during preprocessing, getting wrong results. Any idea what can be the issue.

hollance commented 6 years ago

I haven't tried this myself but I see other people reporting similar issues (with CoreML and Vision).

hassanmasood1 commented 6 years ago

ok, found fix. For me i downgraded xcode to 9 and rebuild and deployed model in device. Now its giving me right results. Surprisingly mobilenet works even on xcode 10 but all others need xcode 9.