How to deploy the model (.pt) or convert to tf model(.pb)

[elvinest]

How to deploy .pt file to production environment (web or mobile) or convert to tensorflow model file (.pb)

I trained my own dataset and generated the last.pt file,I can run detect.py perfectly to predict, but I don’t know how to deploy models(.pt) or convert them to tensorflow model files(.pb)

Hope help me! Thanks.

[github-actions[bot]]

Hello @elvinest, 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 that 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.

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[BernardinD]

Any luck with this?

[ShihuaiXu]

Any luck with this?

[sleepyheead]

Any luck with this?

[glenn-jocher]

@sheerrrr for exporting YOLOv5 PyTorch models to TensorFlow or TFLite see https://github.com/ultralytics/yolov5/pull/1127

[Dutra-Apex]

You can export a torch as a .onnx file using toch.onnx.export From there you can either deploy the .onnx file, or convert it to a .pb file by using tesnorflow onnx backend: https://github.com/onnx/onnx-tensorflow

[glenn-jocher]

@Dutra-Apex that's correct! You can export your .pt model to ONNX format using torch.onnx.export, and then use the ONNX model in various production environments or convert it to TensorFlow's .pb format using the ONNX-TensorFlow converter. For detailed instructions on exporting to ONNX and further conversion, please refer to our documentation. If you encounter any issues or have further questions, feel free to ask here. Happy deploying! 😊🚀