ultralytics / yolov3

YOLOv3 in PyTorch > ONNX > CoreML > TFLite
https://docs.ultralytics.com
GNU Affero General Public License v3.0
10.18k stars 3.44k forks source link

iDetection iOS App source code #257

Closed ghost closed 4 years ago

ghost commented 5 years ago

Hello is there any plan to open source the iOS App code? Thanks.

pannaf commented 5 years ago

I'm wondering this as well. Has anyone else succeeded in putting their PyTorch model on an app? I was able to convert my model to CoreML. I tried to drop the model into this app https://github.com/Ma-Dan/YOLOv3-CoreML with some minor changes, where I: 1) changed the number of classes, 2) changed the feature assertion sizes, and 3) changed the ONNX export in this repo to output the input to the three Yolo layers (instead of the output of the Yolo layers) because I think that's what the app's Yolo class expects as output format. This has been an unsuccessful endeavor.

kbaxx commented 4 years ago

same here :)

github-actions[bot] commented 4 years ago

This issue is stale because it has been open 30 days with no activity. Remove Stale label or comment or this will be closed in 5 days.

glenn-jocher commented 11 months ago

@kbaxx we don't currently have plans to open source the iOS app code. Integrating PyTorch models into mobile apps can be challenging. You may find success by verifying that the CoreML conversion and app's YOLO class expectations align, along with carefully debugging your modifications. Other users may have insights to share. Good luck!