search

NVIDIA-AI-IOT / cuDLA-samples

YOLOv5 on Orin DLA
Other
187 stars 18 forks source link

Quantization of yolov5 #11

Closed zifeiyu-tan closed 2 months ago

zifeiyu-tan commented 10 months ago

If i only want to quantize with int8 in yolov5, how to change this code。

liuanqi-libra7 commented 9 months ago

Hi @tangxiangyu0313 ,

The code in this link has already implemented quantization for YOLOv5. We provide two quantization modes for selection, and you can refer to the README for replication.

Thanks