when applying the model.fuse(), the processing of torchscript export fail. (how to accelerate the model inference when using torchscript depend on libtorch in c++ language？)

[silicon2006]

❔Question

Additional context

[github-actions]

Hello @silicon2006, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@silicon2006 thank you for raising this issue. commit a8751e5 should fix this. Model fusing during export is now enabled and takes effect for all export destinations: torchscript, onnx, and coreml.

Please git pull and try again.

[glenn-jocher]

@silicon2006 also FYI, you can use Netron viewer to verify that the exported models are fused.

[silicon2006]

That's great, I solved this problem yesterday ,but your's solution is much better. thanks!