search

quic / ai-hub-models

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
https://aihub.qualcomm.com
BSD 3-Clause "New" or "Revised" License
438 stars 60 forks source link

[BUG] Mobile BYOM Issue: <insert issue here> OnePlus 9 Pro modelo LE2121 #93

Closed Alexanbezerra closed 1 month ago

Alexanbezerra commented 1 month ago

Describe the issue Please provide details relating to the issue you're hitting, if it is related to performance, accuracy or other model issues with bringing your own model to Qualcomm AI Hub, to deploy to mobile devices.

To Reproduce Please provide clear steps as to how the issue occurred. Either provide a job link or exact steps (i.e. go to xx model, scroll down and click on xx).

Expected behavior A clear and concise description of what you expected to happen.

Stack trace If applicable, add screenshots to help explain your problem.

Host configuration:

Additional context Add any other context about the problem here.

Alexanbezerra commented 1 month ago

O meu aparelho celular é um OnePlus 9 Pro modelo LE2121 com sistema Android

mestrona-3 commented 1 month ago

Hi @Alexanbezerra , please provide more details as to the issue that you're facing. We provide over 100 pre-optimized models that work across Android devices depending on the runtime (tflite, QNN or ONNX) and device you're targeting. We also support bringing your own model to app.aihub.qualcomm.com in various source formats (PyTorch, ONNX, AIMET) and compiling it yourself, to then use the optimized asset on device. Check out the getting started steps, which includes all the devices we currently support by running qai-hub list-devices, we have the Xiaomi Redmi Note 10 5G (onePlus). You can deploy this asset on device by bundling it in your application.