search

ChristianYang37 / fast_yolov7_pytorch

Using pruning and quantization algorithm to accelerate your yolov7's inference.
17 stars 4 forks source link

May I ask how to apply Post-Training Static Quantization on YOLOv7? #2

Open RonaldYuren opened 11 months ago

chensterliu commented 9 months ago

Quantization is stated here https://github.com/ChristianYang37/fast_yolov7_pytorch#quantization

RonaldYuren commented 9 months ago

Can the Post-Training-Quantization can use the "torch.quantization.prepare" , just like your "models /quant_yolo.py"