WongKinYiu / yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
GNU General Public License v3.0
1.98k stars 524 forks source link

yolov4-p7 #61

Open wangerxiao719 opened 2 years ago

wangerxiao719 commented 2 years ago

this code could train yolov4-p7?

WongKinYiu commented 2 years ago

yes

wangerxiao719 commented 2 years ago

i download yolov4-p7.pt in https://github.com/WongKinYiu/ScaledYOLOv4, but it cannot run in this code? what should i do? i do this in order to solve the problem of memory not enough when trainning yolov4-p7 under https://github.com/WongKinYiu/ScaledYOLOv4

WongKinYiu commented 2 years ago

use this branch https://github.com/WongKinYiu/yolor/tree/paper the memory usage are same between scaledyolov4 and yolor.