Open ausk opened 5 months ago
You may use wrong scripts to convert yolov9 models to tensorrt. If your conversion is correct, size of yolov9-c-converted will be about 52% size of yolov8l-v8.1.
We have tested in multiple methods include with/without nms. yolov9-c-converted is about 15~25% faster than yolov8l-v8.1. I suggest you to use official yolov8 code, or tensorrt-yolo to examine speed. We have checked above implementation.
@WongKinYiu I check, and find the yolov9 trt's type is fp32, while others type is fp16. I'll update the table soon.
@WongKinYiu Updated, all of them are the type of fp16 now.
Based on the data, yolov9-c-converted outperforms yolov8l-v8.1 and yolov5x-v6.1 in terms of both fps and model size. Additionally, yolov9-c-converted also slightly surpasses yolov8l-v8.1 and yolov5x-v6.1 in accuracy(MAP).
Thank you for such a great job.
Thanks.
为啥测试要用C++的nms,降低了这个数据的参考意义
s. yolov9-c-converted is about 15~25% faster than yolov8l-v8.1.
请问大佬有没有对比测试yolov9s呢
@ausk
could you help for adding speed of yolov9-t-converted.pt, yolov9-s-converted.pt, yolov9-m-converted.pt to the table, thanks.
看论文估计和yolo10差不多
yolov5 yolov8 yolov9 speed test on T4 (tensorrt )
platform : T4; c++ with nms ; nchw=(1,3,384,640); input (1920, 1080); 200 loops, (already warmed up)
Based on the data,
yolov9-c-converted
outperformsyolov8l-v8.1
andyolov5x-v6.1
in terms of bothfps
andmodel size
. Additionally, yolov9-c-converted also slightly surpasses yolov8l-v8.1 and yolov5x-v6.1 in accuracy(MAP).从数据上看,yolov9-c-converted在帧率和模型大小方面都表现优于yolov8l-v8.1和yolov5x-v6.1。同时,yolov9-c-converted在精度上也略高于yolov8l-v8.1, 高于 yolov5x-v6.1