5

I would like to convert a detectron2 model into a another deeplearning framework i.e. PyTorch, TensorFlow or ONNX. How do I do this conversion?

I can run inference on the detectron2 model with the cfg (which I believe means config in detectron2 lingo).

The goal is to eventually run the Detectron2 model on a Nvidia Jetson Board. So, the goal would be to convert the model.

KamKam
  • 103
  • 1
  • 8
  • I believe detectron2 is implemented in pytorch already. I don't really understand your question – David Jun 28 '21 at 05:55
  • Did you figure it how? Based on this issue, it seems that it is not supported. is it? https://github.com/facebookresearch/detectron2/issues/46 – Maryam Bahrami Jul 29 '21 at 14:02

1 Answers1

2

Since v0.4 you can deploy detectron2 models to torchscript and ONNX. There is more information about it in the documentation (and also example code).

Wilder Galvao
  • 66
  • 6