-
Notifications
You must be signed in to change notification settings - Fork 634
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Different behavior on iphone 12 and Macbook Pro of the same model on the same images #1126
Comments
How large are the differences between the Core ML model on macOS vs iOS? Can you find a single image where the predictions differ significantly? |
Well...there are several images where I get multiple detections when tested on iphone and just a single detection when tested on the macbook. Did I answer your question? Do you mean something else by 'large differences'? |
Usually this has to do with FP32/FP16. Can you try running it on the device with this flag: https://developer.apple.com/documentation/coreml/mlpredictionoptions/2921288-usescpuonly. This will help eliminate if the issue is during conversion of precision related. |
Here is a small example of the outputs we get on different model evaluations using the same model. Overall :
iOS iphone 12 mini accelerated (confidence is last) 21.01.19-15.16.06-R.png 21.02.26-07.58.31-.neg.png 21.02.25-08.37.21-.multi.png 21.01.20-16.25.10-.multi.png 21.02.26-07.56.18-L.C266.768.247.247.png iOS iphone 12mini cpu ONLY (confidence is last): 21.01.19-15.16.06-R.png 21.02.26-07.58.31-.neg.png 21.02.25-08.37.21-.multi.png 21.01.20-16.25.10-.multi.png 21.02.26-07.56.18-L.C266.768.247.247.png simulator - Mac (confidence is last) 21.01.19-15.16.06-R.png 21.02.26-07.58.31-.neg.png 21.02.25-08.37.21-.multi.png 21.01.20-16.25.10-.multi.png 21.02.26-07.56.18-L.C266.768.247.247.png coreMLtools in python on Mac (after conversion from turicreate) 21.01.19-15.16.06-R.png 21.02.26-07.58.31-.neg.png 21.02.25-08.37.21-.multi.png 21.01.20-16.25.10-.multi.png 21.02.26-07.56.18-L.C266.768.247.247.png TuriCreate in python on Mac 21.01.19-15.16.06-R.png 21.02.26-07.58.31-.neg.png 21.02.25-08.37.21-.multi.png 21.01.20-16.25.10-.multi.png 21.02.26-07.56.18-L.C266.768.247.247.png |
Is this still an issue with the latest version of macOS and iOS? |
❓Question
I have trained a custom object detector to detect a specific object of interest through turicreate and then converted my final model to coreML.
I observed that the model behaves differently when integrated in the iphone app and when tested on my laptop. In particular, both the turicreate model and the extracted coreML version of it seem to be more reliable when tested on my MacBook against the same coreML model as part of the iOS app when tested on exactly the same images.
The on-device copy of the coreML model gives more false positives than when tested locally on the same images.
Any thoughts or advise??
Thanks a lot in advance!!
The text was updated successfully, but these errors were encountered: