The demo APP works just fine with deeplabv3.
But instead of using the default deeplabv3 models, I am trying to use detecton2. (we used detectron2 for training and inference, now we want to use it for edge implementation).
Here is what I have achieved and tested successfully in Python:
converted detectron2 to TorchScript using tracing. Validated and got correct inference results.
Optimized the TorchScript model for mobile.
Saved the optimized torchscript model for lite interpreter (.ptl).
IDE environment:
Android Studio.
pytorch lite version: implementation ‘org.pytorch:pytorch_android_lite:1.13.0’
torchvision lite version: implementation ‘org.pytorch:pytorch_android_torchvision_lite:1.13.0’
Error
Following ops cannot be found: [torchvision::nms].
I did go through a lot of posts here and there, unfortunately none was able to solve the problem.
It could be that I am not doing it right.....
So I am working with the Android demo APP for image segmentation with Pytorch.
The demo APP works just fine with deeplabv3. But instead of using the default deeplabv3 models, I am trying to use detecton2. (we used detectron2 for training and inference, now we want to use it for edge implementation).
Here is what I have achieved and tested successfully in Python:
IDE environment:
Error
I did go through a lot of posts here and there, unfortunately none was able to solve the problem. It could be that I am not doing it right.....
Any help will be appreciated.