google-coral / edgetpu

Coral issue tracker (and legacy Edge TPU API source)
https://coral.ai
Apache License 2.0
429 stars 125 forks source link

Coral dev board and YOLO for object detection. #869

Open MECHAAMER opened 1 month ago

MECHAAMER commented 1 month ago

Description

I'm working on training a Yolo model for object detection and plan to use a Google Coral Dev Board for inference. As the Coral documentation recommends, the model should be in the TFLite format with 8-bit quantization for optimal performance.

Thanks to Ultralytics, exporting the model to the required format is straightforward: Python

from ultralytics import YOLO 

model = YOLO("pre_trained_model.pt")

# Export the model to TFLite Edge TPU format 
model.export(format="edgetpu")

In the output, I see: Number of operations that will run on Edge TPU: 425 Number of operations that will run on CPU: 24

My question is: Can I do anything to make all operations run on the TPU for faster processing?

Additionally, are there any other recommended models that might offer better accuracy and lower latency on a Google Coral board?

Thank you all.

Click to expand! ### Issue Type Performance, Support ### Operating System Ubuntu ### Coral Device Dev Board ### Other Devices _No response_ ### Programming Language Python 3.7, Other ### Relevant Log Output _No response_