Bug while running iphone app.

yuna06 commented 5 years ago

Your demo mlmodel file worked, but a model I created from raw data got an error. Does anyone solve the problem?

[error] Screen Shot 2019-08-14 at 3 23 08

classes[c] = Float(featurePointer[offset(channel + 5 + c, cx, cy)])
                    }

2019-08-14 03:12:32.375783+0900 YOLOv3-CoreML[1032:231792] [MC] System group container for systemgroup.com.apple.configurationprofiles path is /private/var/containers/Shared/SystemGroup/systemgroup.com.apple.configurationprofiles
2019-08-14 03:12:32.384252+0900 YOLOv3-CoreML[1032:231792] [MC] Reading from public effective user settings.
YOLOv3-CoreML was compiled with optimization - stepping may behave oddly; variables may not be available.
(lldb)

[environment] python 3.6.5 tensorflow 1.7.0 h5py 2.7.1 Keras 2.1.6 coremltools 0.8

[process]

I have created h5 file using repository below. https://github.com/qqwweee/keras-yolo3 I have modified convert.py as below
```
input_layer = Input(shape=(416, 416, 3))
```
I converted h5 file to mlmodel and ran ios app (Xcode 10.3, iphone6s), and worked but nothing detected and got error above.

yuna06 commented 5 years ago

I have changed numClasses and solved the problem.

let numClasses = 1

robsannaa commented 4 years ago

I didn't want to open an issue because it makes no sense, so I decided to ask in this current issue. I am not confident with Xcode environment and I am trying to build the app to my iPhone. However, I am getting this error:

No profiles for 'net.machinethink.YOLOv3-CoreML' were found: Xcode couldn't find any iOS App Development provisioning profiles matching 'net.machinethink.YOLOv3-CoreML'.

What am I doing wrong?

Ma-Dan / YOLOv3-CoreML

Bug while running iphone app. #12