-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
export error #19
Comments
Hi Ultralytics have a lot of documentation here: https://docs.ultralytics.com/integrations/tflite/ Once you've exported a TFLite file you can compile it for Edge TPU. There is also a guide for that here: https://docs.ultralytics.com/integrations/edge-tpu/ Have you tried these guides already? Thanks! |
thanks for your reply, havent been that pages, anyway, thanks for your code, i have run your tflite model in my m.2 coral from my raspberrypi,but i am stuck in exporting my own yolov5 custom trained model. i will feedback soon. |
Have you also looked at the export instructions in this repository? The reason I didn't suggest that is because Ultralytics seem to support this out-of-the-box now, so their guide is more up to date (and you can use v8 instead of v5). https://github.com/jveitchmichaelis/edgetpu-yolo/blob/main/export.md |
by any chance can you provide us a detailed instruction on how to export .pt model to edgetpu.tflite model?, i have googling this process but still no luck.. thanks a lot.
The text was updated successfully, but these errors were encountered: