edgetpu.ftlite is numpy.int8 but Coral only support uint8 input type

[oscarhuang1117]

Search before asking

• I have searched the YOLOv8 issues and discussions and found no similar questions.

Question

I have used this code ( !yolo export model=/content/drive/MyDrive/yolov8/best.pt format=edgetpu ) in Colab, and successfully obtained \best_saved_model\yolov8s-pose_full_integer_quant_edgetpu.tflite.
But when I use yolov8s-pose_full_integer_quant_edgetpu.tflite on my Coral, it tells me ValueError: Only support uint8 input type, then I check my edgetpu.tflite's type, which is numpy.int8.
Please tell me how to solve this problem, thanks!

Additional

No response

[glenn-jocher]

@oscarhuang1117 hello! It looks like there's a mismatch between the data types expected by the Coral Edge TPU and the ones produced by the export process. To resolve this, you can modify the export process to ensure the model uses uint8 quantization instead of int8. Unfortunately, direct control over this isn't available through the YOLO CLI or API directly.

However, you can manually adjust the quantization parameters in the TensorFlow code before exporting if you have access to the TensorFlow model conversion scripts. If you're using the Ultralytics export functionality, ensure you're using the latest version as updates and fixes are continuously made.

If the issue persists, consider opening an issue on the Ultralytics GitHub page to get specific help or updates on this matter.

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐