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

[Question] Where did your tflite model come from? #86

Closed Ss-shuang123 closed 1 month ago

Ss-shuang123 commented 1 month ago

Your example code is all pytorch related. Is your tflite model reconstructed or converted? Can you provide more detailed information? Because it seems that QNN is more friendly to tiflite support. Very important!!!Thanks a lot!

gustavla commented 1 month ago

Hi @Ss-shuang123,

We go from PyTorch to TFLite using AI Hub compile jobs. You can read more about them here: https://app.aihub.qualcomm.com/docs/hub/compile_examples.html#compiling-pytorch-to-tflite